© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93927
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     pleaſure
    -0.94
     ſche
    -0.93
     quæ
    -0.91
     Monfieur
    -0.91
     ſtate
    -0.90
     houſe
    -0.90
     ſame
    -0.89
     habet
    -0.88
     ſeveral
    -0.85
     Diſ
    -0.84
    POSITIVE LOGITS
    NUMX
    1.26
    liothèque
    0.98
    <bos>
    0.95
    etheless
    0.95
    ficulties
    0.95
    itects
    0.94
    LookAnd
    0.94
    yntaxException
    0.94
    ellites
    0.93
    CELLANEOUS
    0.93
    Activations Density 0.555%

    No Known Activations