© 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. 12-RES-MATRYOSHKA-DC
    7. 22903
    Prev
    Next
    INDEX
    Explanations

    the presence of error or issues related to code or compilation messages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Kanpo
    -0.78
    linux
    -0.77
     Brew
    -0.75
    躇
    -0.74
    SIGNAL
    -0.72
     Lons
    -0.72
    LookAnd
    -0.71
    igg
    -0.71
    winder
    -0.69
    brew
    -0.68
    POSITIVE LOGITS
     ***
    0.88
     compétence
    0.79
     Camden
    0.72
    !***
    0.72
    enheim
    0.72
     Merton
    0.71
    таратура
    0.71
    asus
    0.70
     turística
    0.69
    ***
    0.68
    Activations Density 0.009%

    No Known Activations