© 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. 43594
    Prev
    Next
    INDEX
    Explanations

    rest

    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
    RenderAtEndOf
    -1.01
     rest
    -0.84
     فريبيس
    -0.73
     rests
    -0.72
     mxArray
    -0.72
     rested
    -0.71
    دانشنامهٔ
    -0.70
     invokingState
    -0.69
    StoryboardSegue
    -0.68
    QMetaType
    -0.67
    POSITIVE LOGITS
    hankelijk
    0.40
     então
    0.40
     tijde
    0.40
    ówczas
    0.39
     []:
    0.39
     Fällen
    0.38
    walla
    0.38
     noemen
    0.37
    ❯
    0.37
     entonces
    0.36
    Activations Density 0.141%

    No Known Activations