© 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. 21555
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names associated with political figures and officials

    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
    tså
    -0.49
    rops
    -0.47
    Itoa
    -0.46
    HasForeignKey
    -0.45
    '
    -0.42
    siella
    -0.41
     star
    -0.41
    Garage
    -0.40
    oara
    -0.40
     series
    -0.40
    POSITIVE LOGITS
     Roskov
    0.95
     الحره
    0.83
    Przypisy
    0.83
    GeneratedCode
    0.78
     referenties
    0.77
    省市镇
    0.75
    migrationBuilder
    0.75
     Numerade
    0.75
    VIAF
    0.74
    Билгалдахарш
    0.74
    Activations Density 0.041%

    No Known Activations