© 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. 4-CLT-HP
    7. 352
    Prev
    Next
    INDEX
    Explanations

    Val

    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
    icrous
    -0.54
    himovic
    -0.50
     therefrom
    -0.50
    ously
    -0.50
    stest
    -0.48
    WebpackPlugin
    -0.48
     Battista
    -0.48
     subs
    -0.47
    образ
    -0.47
     distributive
    -0.47
    POSITIVE LOGITS
     ***!
    0.59
    fjspx
    0.55
    posedge
    0.52
     bezeichneter
    0.51
    ThroughAttribute
    0.49
    OrWhiteSpace
    0.47
    DeleteMapping
    0.46
    λίου
    0.45
     craindre
    0.44
    TintMode
    0.43
    Activations Density 0.007%

    No Known Activations