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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 998
    Prev
    Next
    INDEX
    Explanations

    instances of enablement and support, often using the word "allow"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageState
    -0.70
    delwed
    -0.61
    了自己的
    -0.61
     kanyang
    -0.60
    Personensuche
    -0.60
     swój
    -0.59
     svůj
    -0.59
     своя
    -0.58
     الوطنيه
    -0.58
     swoją
    -0.56
    POSITIVE LOGITS
     us
    1.05
     me
    0.82
     them
    0.81
     people
    0.78
     you
    0.73
     companies
    0.68
    makeText
    0.66
     him
    0.65
     designers
    0.62
     everyone
    0.59
    Activations Density 0.876%

    No Known Activations