Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 26900
    Prev
    Next
    INDEX
    Explanations

    repeated zero values indicating the absence of specific information or content

    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
    MigrationBuilder
    -0.75
     Meksiku
    -0.68
     wireType
    -0.63
    fromCharCode
    -0.62
    thâu
    -0.60
    WriteTagHelper
    -0.57
     />\
    -0.56
     tartalomajánló
    -0.56
    aarrggbb
    -0.56
    rrggbb
    -0.55
    POSITIVE LOGITS
    AnimationsModule
    0.57
     presidencial
    0.55
     plads
    0.54
    }{*}{}
    0.54
    KELEY
    0.53
     kawaida
    0.52
     trecut
    0.50
    inį
    0.50
    antaranya
    0.49
     seier
    0.49
    Activations Density 0.006%

    No Known Activations