© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13859
    Prev
    Next
    INDEX
    Explanations

    mathematical equations related to cipher spaces and encryption methods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.19
    0.6%
    1978
    +0.14
    0.4%
    184
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.19
    0.00
    93
    +0.14
    0.02
    1251
    +0.12
    0.02
    Negative Logits
     autorytatywna
    -0.79
     playboy
    -0.74
    GEBURTSDATUM
    -0.70
    توض
    -0.66
    sightly
    -0.65
     spokespersons
    -0.62
     schoolmaster
    -0.62
     deafening
    -0.61
     endeavouring
    -0.61
     thoughtless
    -0.61
    POSITIVE LOGITS
     dises
    1.37
     illi
    1.29
     erec
    1.28
     poff
    1.21
     aen
    1.20
     blos
    1.19
     sii
    1.19
     quos
    1.17
     effe
    1.17
     grati
    1.16
    Activations Density 0.072%

    No Known Activations