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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40529
    Prev
    Next
    INDEX
    Explanations

    science

    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
     poffe
    -0.86
     ſche
    -0.86
     itſelf
    -0.85
     ſtate
    -0.85
     houſe
    -0.84
     auffi
    -0.83
     raiſ
    -0.81
     Majefty
    -0.80
     paſſ
    -0.78
     myſelf
    -0.77
    POSITIVE LOGITS
    rain
    0.56
    ous
    0.53
     Con
    0.53
    ez
    0.52
    yez
    0.52
    ing
    0.50
    ating
    0.49
    principalColumn
    0.49
    dent
    0.48
    FormData
    0.46
    Activations Density 0.842%

    No Known Activations