© 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. 4-CLT-HP
    7. 212
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     كمان
    -0.60
    AutoScaleMode
    -0.54
    IBAction
    -0.54
     ImportError
    -0.54
    ToTable
    -0.52
     ankaŭ
    -0.50
     invokingState
    -0.50
     exposure
    -0.49
    annulation
    -0.49
    detectChanges
    -0.48
    POSITIVE LOGITS
     lenker
    0.82
    HtmlAttribute
    0.59
    setVerticalGroup
    0.54
    webElementXpaths
    0.49
    Personensuche
    0.49
     MongoClient
    0.48
    saraba
    0.48
    ']>
    0.48
     pure
    0.47
     transfieras
    0.47
    Activations Density 0.047%

    No Known Activations