© 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. 5-CLT-HP
    7. 91719
    Prev
    Next
    INDEX
    Explanations

    ease or improvement

    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
    曖昧さ回避
    -0.90
    IContainer
    -0.78
     invokingState
    -0.75
    存于互联网档案馆
    -0.75
    AnimationsModule
    -0.73
    IBarButtonItem
    -0.73
    DMETHOD
    -0.73
    ftagPool
    -0.73
     kasarigan
    -0.72
    MLLoader
    -0.69
    POSITIVE LOGITS
    さんです
    0.40
    endsection
    0.39
     more
    0.36
    enderror
    0.35
     its
    0.34
     those
    0.34
     اللي
    0.33
    ahuila
    0.31
    이다
    0.31
     Derfor
    0.31
    Activations Density 0.086%

    No Known Activations