© 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. 96896
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    ISupport
    -0.89
     مرئيه
    -0.63
    /**
    -0.63
    AnchorStyles
    -0.63
    SizeF
    -0.60
    esez
    -0.60
    IContainer
    -0.59
    Бахар
    -0.58
    kloped
    -0.57
    __':
    -0.54
    POSITIVE LOGITS
     incentive
    0.57
    inkai
    0.56
     deterrent
    0.54
     deterrence
    0.52
     mitigation
    0.50
    agaan
    0.50
     consolation
    0.48
    stående
    0.48
     entré
    0.47
     garan
    0.47
    Activations Density 0.004%

    No Known Activations