© 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. 0-CLT-HP
    7. 1313
    Prev
    Next
    INDEX
    Explanations

    code

    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
    RTLU
    -0.56
     beginnetje
    -0.55
    EndProject
    -0.54
    gebra
    -0.53
     ब्रेकडाउन
    -0.53
     مُعرِّف
    -0.52
     revêtement
    -0.52
    #+#
    -0.51
    OrNil
    -0.51
     Clancy
    -0.50
    POSITIVE LOGITS
    \{\\
    0.66
    PerformLayout
    0.65
    Cyfeiriadau
    0.64
    getMinutes
    0.62
    ilat
    0.55
    IntoConstraints
    0.54
    gdx
    0.53
    ($(
    0.51
     فريبيس
    0.51
    idist
    0.51
    Activations Density 0.675%

    No Known Activations