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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16587
    Prev
    Next
    INDEX
    Explanations

    URL patterns and web links

    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
    saraba
    -0.62
     lenker
    -0.57
    يكب
    -0.53
     personeel
    -0.52
     pensées
    -0.52
    Tikang
    -0.51
     luminosa
    -0.51
     ansvar
    -0.50
     EconPapers
    -0.50
    RenderAtEndOf
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.82
    extAlignment
    0.69
    SequentialGroup
    0.61
    DTD
    0.61
    twimg
    0.56
    abestanden
    0.55
    MeasureSpec
    0.55
    EndInit
    0.54
     iprot
    0.54
    ettet
    0.53
    Activations Density 0.001%

    No Known Activations