© 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. 745
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by numbers indicating years

    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
    TProtocol
    -0.55
     iprot
    -0.54
     dAtA
    -0.51
     Tư
    -0.50
     '\\;'
    -0.47
     phun
    -0.46
     ModelExpression
    -0.46
    پیوند
    -0.45
    UnifiedTopology
    -0.44
    Glej
    -0.44
    POSITIVE LOGITS
    columbia
    0.57
    存于互联网档案馆
    0.56
    šče
    0.52
     skla
    0.51
    Espèce
    0.51
    gelöst
    0.51
    enuto
    0.50
    EndInit
    0.50
    Fns
    0.48
     Wicidata
    0.48
    Activations Density 0.137%

    No Known Activations