© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 981
    Prev
    Next
    INDEX
    Explanations

    descriptions of systems/methods

    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
     variety
    -1.08
    ⓧ
    -0.99
    variety
    -0.96
     fatal
    -0.86
    quarter
    -0.84
     quarter
    -0.83
     fatality
    -0.83
    Quarter
    -0.81
     Quarter
    -0.79
     variedad
    -0.75
    POSITIVE LOGITS
    دانشنامهٔ
    0.48
     Weise
    0.45
    izing
    0.44
    posedge
    0.43
    hassee
    0.40
    Eksteraj
    0.40
    cy
    0.39
    ead
    0.38
     Unido
    0.38
     pijn
    0.38
    Activations Density 0.294%

    No Known Activations