© 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. 14933
    Prev
    Next
    INDEX
    Explanations

    outre

    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
    outre
    -1.67
     outre
    -0.76
     Outre
    -0.68
    addPreferredGap
    -0.67
     MainAxisSize
    -0.58
    المناصب
    -0.56
     consultato
    -0.56
     esterni
    -0.52
     صوتيه
    -0.50
    RTDA
    -0.50
    POSITIVE LOGITS
    GEBURTSDATUM
    0.74
    wydd
    0.54
    FormTagHelper
    0.51
    AddWithValue
    0.51
     spu
    0.50
    iloc
    0.49
    JsonProperty
    0.48
    λω
    0.48
    asure
    0.46
     nakalista
    0.46
    Activations Density 0.003%

    No Known Activations