© 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. 95113
    Prev
    Next
    INDEX
    Explanations

    Fall, Red, length

    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
    aarrggbb
    -0.86
     CreateTagHelper
    -0.73
    transQ
    -0.71
    MessageOf
    -0.70
    abstractmethod
    -0.69
    adpleegd
    -0.69
    BufferException
    -0.68
     للمعارف
    -0.67
    الدراسه
    -0.65
    VersionUID
    -0.65
    POSITIVE LOGITS
     notes
    0.42
     {_
    0.42
     tham
    0.40
    fee
    0.39
    things
    0.38
    apnews
    0.38
    writeField
    0.38
     tö
    0.37
    hos
    0.37
    Kenn
    0.37
    Activations Density 0.105%

    No Known Activations