© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
    InputBorder
    -0.74
     ProtoMessage
    -0.69
     MotionEvent
    -0.68
     jLabel
    -0.68
     nahilalakip
    -0.67
    =$?
    -0.62
     note
    -0.59
    brigens
    -0.59
    ukunft
    -0.59
    setVerticalGroup
    -0.59
    POSITIVE LOGITS
    そこで
    1.13
     here
    0.92
     Daarom
    0.91
    今回は
    0.87
     daarom
    0.85
    为此
    0.84
     derfor
    0.79
     deshalb
    0.77
    here
    0.75
     purpose
    0.75
    Activations Density 0.862%

    No Known Activations