© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73543
    Prev
    Next
    INDEX
    Explanations

    range

    np_max-act-logits · 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
    Datuak
    -0.95
    دانشنامهٔ
    -0.92
     kasarigan
    -0.91
     nahilalakip
    -0.90
     Италијани
    -0.89
     виправивши
    -0.88
     Administrativna
    -0.81
     ligiloj
    -0.81
     BrowserModule
    -0.80
    sizeCache
    -0.77
    POSITIVE LOGITS
    multirow
    0.42
    tü
    0.39
    young
    0.39
     tot
    0.39
     mé
    0.39
    伏
    0.38
    mes
    0.37
     mee
    0.36
    men
    0.36
    tomb
    0.35
    Activations Density 0.002%

    No Known Activations