© 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. 5-CLT-HP
    7. 93934
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    cdnjs
    -0.49
     I
    -0.49
    endroit
    -0.46
    Gön
    -0.46
    acto
    -0.45
     easy
    -0.45
    anueva
    -0.45
    itaries
    -0.45
     normal
    -0.44
     Polda
    -0.43
    POSITIVE LOGITS
     estekak
    0.90
    ########.
    0.77
    
    0.76
     betweenstory
    0.70
    ThroughAttribute
    0.69
     समीक्षाओं
    0.69
    Obrázky
    0.68
    SBATCH
    0.67
     wears
    0.66
    Personensuche
    0.66
    Activations Density 0.002%

    No Known Activations