© 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. 1-CLT-HP
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ligiloj
    -0.54
    före
    -0.47
    förs
    -0.46
    ről
    -0.45
    licité
    -0.45
    väg
    -0.40
    —
    -0.39
    BagConstraints
    -0.39
     connexes
    -0.39
    KeyStore
    -0.38
    POSITIVE LOGITS
     myſelf
    1.13
     Monfieur
    1.09
     Majefty
    1.02
     itſelf
    0.99
     purpoſe
    0.98
     himſelf
    0.94
     Diſ
    0.94
     Efq
    0.93
     themſelves
    0.92
     theſe
    0.92
    Activations Density 0.054%

    No Known Activations