© 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. 17159
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or choices

    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
    Negative Logits
    znál
    -0.68
     Mezz
    -0.63
     tecla
    -0.63
    ">{{$
    -0.60
     Tamb
    -0.59
     EVER
    -0.56
     SQLException
    -0.56
     Haver
    -0.56
    "><?=
    -0.56
     Fet
    -0.56
    POSITIVE LOGITS
     estimés
    0.75
    uesia
    0.75
    stylers
    0.68
    mmation
    0.67
    Lähteet
    0.66
    CellStyle
    0.64
    DllImport
    0.60
     виправивши
    0.60
    CppCodeGen
    0.60
    orari
    0.59
    Activations Density 0.022%

    No Known Activations