© 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. 92625
    Prev
    Next
    INDEX
    Explanations

    manually

    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
    -1.23
    脚注の使い方
    -1.09
    ScopeManager
    -1.01
    CloseOperation
    -0.96
     Roskov
    -0.91
    ✨:
    -0.89
    AndEndTag
    -0.86
    TagMode
    -0.85
    WebVitals
    -0.85
     يتيمه
    -0.84
    POSITIVE LOGITS
    or
    0.43
    als
    0.41
    ore
    0.41
     algunas
    0.40
     (
    0.40
    ry
    0.39
    cy
    0.39
     alguna
    0.39
    log
    0.39
    μ
    0.38
    Activations Density 0.002%

    No Known Activations