© 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. 1-CLT-HP
    7. 13029
    Prev
    Next
    INDEX
    Explanations

    it

    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
     is
    -1.17
     has
    -0.93
     was
    -0.89
     lacks
    -0.85
     teaches
    -0.82
     contains
    -0.82
     hasn
    -0.81
     doesn
    -0.81
     provides
    -0.80
     represents
    -0.80
    POSITIVE LOGITS
    ,
    0.73
    .
    0.72
     to
    0.69
    Are
    0.68
    are
    0.64
     Are
    0.63
     from
    0.63
     with
    0.59
     ARE
    0.57
     and
    0.57
    Activations Density 0.032%

    No Known Activations