© 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. 1-CLT-HP
    7. 15337
    Prev
    Next
    INDEX
    Explanations

    ISO

    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
     ISO
    -0.67
     <<<<<<<<<<<<<<
    -0.66
    __*/
    -0.62
    Statics
    -0.58
    ISO
    -0.56
    !*\
    -0.56
    ########.
    -0.55
     mushrooms
    -0.52
    MLLoader
    -0.52
    toHaveBeenCalled
    -0.51
    POSITIVE LOGITS
    saraba
    0.56
    UIControlState
    0.53
    rrggbb
    0.50
     fédé
    0.49
    COUVER
    0.48
    adze
    0.47
    Région
    0.47
     NKC
    0.46
     GridLayout
    0.46
    apatalk
    0.46
    Activations Density 0.009%

    No Known Activations