© 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. 91929
    Prev
    Next
    INDEX
    Explanations

    responsibilities and issues

    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
     surprises
    -0.88
     felt
    -0.86
     secrets
    -0.77
     surprise
    -0.76
    secrets
    -0.76
     studied
    -0.73
     surprising
    -0.72
    ya
    -0.71
    sibilities
    -0.71
    felt
    -0.69
    POSITIVE LOGITS
    ValueStyle
    0.78
    RegressionTest
    0.57
     ProtoMessage
    0.57
    évaluateur
    0.57
    StructEnd
    0.57
    posedge
    0.55
    aarrggbb
    0.50
    ViewInit
    0.47
    ">//
    0.45
    المشاركات
    0.45
    Activations Density 0.032%

    No Known Activations