© 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. 31054
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or metrics related to performance

    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
     mCurrent
    -0.55
     samband
    -0.54
     esetben
    -0.54
     confidentialité
    -0.50
    最快更新
    -0.50
     effetto
    -0.47
    hatian
    -0.47
    来到了
    -0.46
     kiin
    -0.46
     álla
    -0.46
    POSITIVE LOGITS
    enumi
    0.86
    Autoritní
    0.73
    Diweddarwch
    0.72
    parsedMessage
    0.70
     estekak
    0.69
    tagHelperRunner
    0.65
    GOTREF
    0.64
    aarrggbb
    0.64
    contentLoaded
    0.63
    enumii
    0.63
    Activations Density 0.029%

    No Known Activations