© 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. 0-CLT-HP
    7. 42286
    Prev
    Next
    INDEX
    Explanations

    holding, gripping, or manipulating

    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
    ha
    -0.49
     original
    -0.43
    ch
    -0.41
     general
    -0.40
     one
    -0.40
     given
    -0.40
     for
    -0.40
     from
    -0.40
    ).
    -0.40
     total
    -0.40
    POSITIVE LOGITS
     '\\;'
    1.09
     متعلقه
    1.03
    FontOfSize
    1.02
     nahilalakip
    1.00
     betweenstory
    0.87
     ExecuteAsync
    0.87
    rrggbb
    0.85
     Majefty
    0.85
     BorderSide
    0.84
     BoxFit
    0.84
    Activations Density 1.639%

    No Known Activations