© 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. 5-CLT-HP
    7. 96249
    Prev
    Next
    INDEX
    Explanations

    genetics

    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
     alignment
    -0.53
     condensation
    -0.45
    ologist
    -0.45
    金山
    -0.44
     abbraccio
    -0.44
     assay
    -0.43
    asma
    -0.43
    endpush
    -0.42
     evaluation
    -0.42
     abrazo
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.76
    findpost
    0.70
    adpleegd
    0.69
    ScopeManager
    0.69
    MigrationBuilder
    0.60
     '\\;'
    0.60
    /***/
    0.58
     ProtoMessage
    0.57
     мәкалә
    0.56
    InstrumentedTest
    0.55
    Activations Density 0.005%

    No Known Activations