© 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. 5-CLT-HP
    7. 92702
    Prev
    Next
    INDEX
    Explanations

    academic/research writing

    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
    SequentialGroup
    -1.02
    UnsafeEnabled
    -0.89
    writeField
    -0.84
    ReusableCell
    -0.82
    WebVitals
    -0.78
    enterOuterAlt
    -0.77
     wireType
    -0.74
    principalColumn
    -0.72
    matchCondition
    -0.71
     transfieras
    -0.70
    POSITIVE LOGITS
     re
    0.53
     Leap
    0.46
     programs
    0.41
    ніципа
    0.40
     Programs
    0.39
    distributions
    0.38
     programmes
    0.37
    utenant
    0.37
     perspectiva
    0.37
     Programmes
    0.37
    Activations Density 0.009%

    No Known Activations