© 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. 888
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people named Michael

    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
    805
    +0.16
    0.6%
    1624
    +0.15
    0.6%
    1741
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.16
    0.04
    1624
    +0.15
    0.04
    1942
    +0.11
    0.03
    Negative Logits
     attesa
    -0.51
     töd
    -0.49
     święta
    -0.48
    arranging
    -0.47
     przeds
    -0.47
     isoliert
    -0.46
     antioxidants
    -0.46
     lynx
    -0.46
     updatedAt
    -0.45
     fulness
    -0.45
    POSITIVE LOGITS
     Michael
    1.42
    Michael
    1.34
     michael
    1.25
     MICHAEL
    1.21
    MICHAEL
    1.19
    michael
    1.18
     Micha
    1.04
     Chapitre
    0.98
     Traité
    0.98
     Miche
    0.97
    Activations Density 0.035%

    No Known Activations