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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1937
    Prev
    Next
    INDEX
    Explanations

    Latin phrases and legal terms

    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
    1343
    +0.12
    0.3%
    1150
    +0.10
    0.3%
    1556
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.03
    1556
    +0.10
    0.02
    1851
    +0.10
    0.02
    Negative Logits
     ejus
    -0.64
     nomine
    -0.61
     pecuni
    -0.56
    scienced
    -0.55
    atguigu
    -0.55
     signora
    -0.55
     quæ
    -0.55
     Vergine
    -0.55
     signor
    -0.54
     eorum
    -0.53
    POSITIVE LOGITS
     minimalis
    0.67
     optik
    0.63
     Tüm
    0.63
     karbon
    0.63
     habile
    0.61
     Sı
    0.59
     /**
    
    0.58
     actualité
    0.58
     Pax
    0.58
     malheure
    0.58
    Activations Density 0.219%

    No Known Activations