© 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. 94852
    Prev
    Next
    INDEX
    Explanations

    technical, software-related content

    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
    tagHelperRunner
    -0.70
    évaluateur
    -0.54
     FAVOR
    -0.52
     servic
    -0.52
    lai
    -0.52
    WindowConstants
    -0.51
    oks
    -0.49
    ysis
    -0.48
     TextAppearance
    -0.48
    a
    -0.46
    POSITIVE LOGITS
    baomidou
    0.59
    ated
    0.57
    }>;
    0.56
    eming
    0.54
    RegistryLite
    0.53
    __*/
    0.53
    Dreaming
    0.53
    reonine
    0.53
    ộn
    0.52
    ^*)
    0.52
    Activations Density 0.576%

    No Known Activations