© 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. 4462
    Prev
    Next
    INDEX
    Explanations

    of

    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
    FieldNumber
    -0.79
     contextLoads
    -0.71
    UnknownFieldSet
    -0.67
     fallu
    -0.67
    ########.
    -0.66
    migrationBuilder
    -0.65
    ScopeManager
    -0.65
     tartalomajánló
    -0.64
     ControllerBase
    -0.63
     automatiques
    -0.63
    POSITIVE LOGITS
     all
    0.63
     final
    0.51
     last
    0.50
     finalized
    0.48
    on
    0.48
     every
    0.47
     (-
    0.46
     individual
    0.46
     finished
    0.45
     everything
    0.45
    Activations Density 0.001%

    No Known Activations