© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    the

    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
    tagHelperRunner
    -0.85
    ſelves
    -0.84
     légende
    -0.83
    FunctionFlags
    -0.77
     Monfieur
    -0.77
     كومونز
    -0.76
    IndentedString
    -0.76
     Majefty
    -0.73
    ſelf
    -0.70
     myſelf
    -0.70
    POSITIVE LOGITS
     reason
    0.74
     time
    0.63
    ,
    0.50
    reason
    0.49
    time
    0.49
    times
    0.49
     why
    0.43
     raison
    0.41
     this
    0.40
     times
    0.40
    Activations Density 0.002%

    No Known Activations