© 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. 0-CLT-HP
    7. 41712
    Prev
    Next
    INDEX
    Explanations

    public

    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
     public
    -2.42
    public
    -1.95
     Public
    -1.84
    Public
    -1.77
     PUBLIC
    -1.49
     öffentliche
    -1.47
     público
    -1.41
    PUBLIC
    -1.39
     öffentlichen
    -1.38
     publique
    -1.30
    POSITIVE LOGITS
     Monfieur
    1.04
     houſe
    0.95
     Majefty
    0.90
     itſelf
    0.89
     Houſe
    0.87
     Efq
    0.87
     myſelf
    0.86
     Reſ
    0.82
     Cæsar
    0.82
     Diſ
    0.80
    Activations Density 0.077%

    No Known Activations