© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72323
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
    DeleteBehavior
    -0.70
     kasarigan
    -0.68
     Allociné
    -0.66
    StructEnd
    -0.66
     CURIAM
    -0.62
    MethodManager
    -0.59
    OGND
    -0.58
    complexContent
    -0.58
    CodeAttribute
    -0.58
     StatelessWidget
    -0.57
    POSITIVE LOGITS
     obtained
    0.52
     perspectives
    0.51
     obtains
    0.50
    excellents
    0.46
     فريبيس
    0.45
     consolidate
    0.45
     consec
    0.44
    Perspectives
    0.43
     obtain
    0.43
     efficiency
    0.42
    Activations Density 0.000%

    No Known Activations