© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 143
    Prev
    Next
    INDEX
    Explanations

    away

    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
     Squash
    -0.49
    FormUrlEncoded
    -0.47
     squash
    -0.44
    beto
    -0.44
     useState
    -0.44
     ["",
    -0.42
    uan
    -0.42
     noten
    -0.41
     pronto
    -0.41
    UAN
    -0.41
    POSITIVE LOGITS
     rides
    0.70
     viaggi
    0.68
     فريبيس
    0.67
    Portail
    0.66
    RegressionTest
    0.65
    InputBorder
    0.64
     للاسماء
    0.64
    Personendaten
    0.62
    addPreferredGap
    0.61
     ride
    0.59
    Activations Density 0.001%

    No Known Activations