© 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. 0-CLT-HP
    7. 38846
    Prev
    Next
    INDEX
    Explanations

    activate

    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
    featureID
    -0.94
     myſelf
    -0.80
     Theſe
    -0.78
     насељу
    -0.77
    Tikang
    -0.77
     escalate
    -0.74
    pexpr
    -0.74
     Monfieur
    -0.73
    BeginContext
    -0.73
     activate
    -0.73
    POSITIVE LOGITS
     an
    0.61
     the
    0.56
     it
    0.56
     our
    0.54
     a
    0.52
     her
    0.52
     those
    0.51
     its
    0.50
     some
    0.50
     both
    0.46
    Activations Density 0.098%

    No Known Activations