© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3834
    Prev
    Next
    INDEX
    Explanations

    instructions/how-to

    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
     should
    -0.68
    should
    -0.56
    RECOMMENDED
    -0.55
    Should
    -0.52
     Should
    -0.52
     SHOULD
    -0.47
    recommended
    -0.46
     solltest
    -0.45
     right
    -0.45
     sollte
    -0.45
    POSITIVE LOGITS
    verwijspagina
    0.84
    InitVars
    0.81
    findpost
    0.78
     $_"
    0.78
    IndentedString
    0.73
     doubtnut
    0.70
    SerializedSize
    0.70
    __(/*!
    0.69
    lankton
    0.69
    RenderAtEndOf
    0.69
    Activations Density 0.013%

    No Known Activations