© 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. 4-CLT-HP
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    accustomed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IndexError
    -0.59
     Efq
    -0.49
     Tev
    -0.47
    atase
    -0.47
     tarp
    -0.47
    ÚS
    -0.46
     webpack
    -0.45
     Monfieur
    -0.45
    ZIONE
    -0.44
    NNN
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    -------
    0.60
    ద్య
    0.60
     [
    0.59
    rrggbb
    0.58
     चीज़ों
    0.57
     brancas
    0.56
    enumi
    0.56
    "
    0.53
     autorytatywna
    0.52
    Activations Density 0.003%

    No Known Activations