© 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. 5-CLT-HP
    7. 93167
    Prev
    Next
    INDEX
    Explanations

    Beginning of a block of text

    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
     nakalista
    -0.59
     Effort
    -0.59
     Trial
    -0.57
    ukone
    -0.56
    Jeografia
    -0.54
     Administrativna
    -0.53
     الحره
    -0.53
     Auto
    -0.52
     vuitton
    -0.52
    oredCriteria
    -0.52
    POSITIVE LOGITS
    :+:
    0.60
    reportWebVitals
    0.60
     AssemblyCulture
    0.59
    بوابة
    0.54
    hematical
    0.51
    ersk
    0.50
     tornare
    0.49
     végétale
    0.48
    AutoScaleMode
    0.48
     człowie
    0.47
    Activations Density 0.001%

    No Known Activations