© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45346
    Prev
    Next
    INDEX
    Explanations

    member

    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
    ConstraintMaker
    -1.13
    IntoConstraints
    -1.07
    adaptiveStyles
    -1.00
    member
    -0.99
    UserScript
    -0.97
    ftagPool
    -0.96
    expandindo
    -0.96
    +#+#
    -0.95
     linkovi
    -0.95
    rrggbb
    -0.89
    POSITIVE LOGITS
    InkWell
    0.43
    après
    0.43
     other
    0.43
    adze
    0.41
     single
    0.40
     ans
    0.40
     space
    0.40
     full
    0.40
     թ
    0.40
    անո
    0.39
    Activations Density 0.245%

    No Known Activations