© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25577
    Prev
    Next
    INDEX
    Explanations

    terms related to expert witnesses and their testimonies

    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
    IntoConstraints
    -0.90
    cydow
    -0.76
    ">//
    -0.76
    chomp
    -0.75
    parsedMessage
    -0.75
    ScopeManager
    -0.74
    AnchorStyles
    -0.73
     Walkover
    -0.70
    posedge
    -0.69
    igshid
    -0.69
    POSITIVE LOGITS
    migrationBuilder
    0.45
     foglal
    0.44
    ishwa
    0.44
     braccia
    0.43
    anggap
    0.43
    accepted
    0.42
    郁
    0.41
    كال
    0.41
     specifically
    0.41
     eccell
    0.40
    Activations Density 0.011%

    No Known Activations