© 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. 0-CLT-HP
    7. 93558
    Prev
    Next
    INDEX
    Explanations

    example

    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
    
    -0.65
     الرياضيه
    -0.48
    큼
    -0.47
    xtype
    -0.47
    SBATCH
    -0.46
    oform
    -0.46
    otheby
    -0.46
     cámara
    -0.45
     disambiguazione
    -0.44
     TextAppearance
    -0.44
    POSITIVE LOGITS
    Bronnen
    0.65
    endphp
    0.62
    Hozzáférés
    0.61
    Fprintf
    0.57
    writeFieldEnd
    0.57
    าหลี
    0.57
     Wirk
    0.55
     Availability
    0.54
     setback
    0.54
     Roskov
    0.53
    Activations Density 0.022%

    No Known Activations