© 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. 20-CLT-HP
    7. 76189
    Prev
    Next
    INDEX
    Explanations

    Human biology/studies

    np_max-act-logits · 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
    AttributeSet
    -0.76
    weile
    -0.68
    OrNil
    -0.66
    expandindo
    -0.62
    Ход
    -0.62
    GOTREF
    -0.59
    __*/
    -0.54
    ][:
    -0.54
     wireType
    -0.53
    __(/*!
    -0.53
    POSITIVE LOGITS
    Rohy
    0.52
    immun
    0.46
    oidal
    0.45
     immun
    0.45
     Immun
    0.43
    RTLR
    0.43
    ITest
    0.43
     <<<<<<<<<<<<<<
    0.42
     onAnimation
    0.42
    estinal
    0.42
    Activations Density 0.000%

    No Known Activations