© 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. 41050
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
     ―――――
    -0.78
     myſelf
    -0.74
     ་་
    -0.73
     itſelf
    -0.71
    leſs
    -0.68
     ――――――――
    -0.66
     fon
    -0.66
     Eſ
    -0.66
     zir
    -0.63
     XNUMX
    -0.61
    POSITIVE LOGITS
    
    0.77
    Espèce
    0.69
     lány
    0.68
     bocca
    0.66
    <bos>
    0.65
     chré
    0.63
     syke
    0.63
     popoli
    0.63
     hâte
    0.63
     közül
    0.62
    Activations Density 0.054%

    No Known Activations