© 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. 12-RES-MATRYOSHKA-DC
    7. 8400
    Prev
    Next
    INDEX
    Explanations

    a high frequency of the pronoun "I."

    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
    rrggbb
    -0.85
    principalTable
    -0.82
    Geplaatst
    -0.79
    InjectAttribute
    -0.77
    VIAF
    -0.77
     mijne
    -0.72
    MigrationBuilder
    -0.69
    ViewFeatures
    -0.69
     okuyayım
    -0.68
    HasForeignKey
    -0.67
    POSITIVE LOGITS
    PROTOBUF
    0.64
    cepción
    0.63
    rungsseite
    0.61
    ră
    0.56
    RefNanny
    0.53
    paf
    0.50
    wark
    0.50
     Morin
    0.48
     Mundi
    0.48
     Mins
    0.48
    Activations Density 0.105%

    No Known Activations