© 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. 1-CLT-HP
    7. 15314
    Prev
    Next
    INDEX
    Explanations

    evitar

    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
     zoude
    -0.80
    turnstile
    -0.73
     feroit
    -0.69
     moschino
    -0.69
    Vidite
    -0.69
     auroit
    -0.68
     EconPapers
    -0.67
     avoient
    -0.65
     TextAppearance
    -0.64
    ChildScrollView
    -0.64
    POSITIVE LOGITS
    WEBPACK
    0.66
    ↵↵
    0.53
    BeginInit
    0.53
    __*/
    0.51
     -
    0.50
     too
    0.49
     bij
    0.48
    ("}\
    0.48
     later
    0.47
    :"-"`
    0.47
    Activations Density 0.001%

    No Known Activations