© 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. 92357
    Prev
    Next
    INDEX
    Explanations

    0

    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
     no
    -0.52
    )
    -0.47
    >
    -0.46
    wise
    -0.46
    .
    -0.45
     V
    -0.43
    <eos>
    -0.43
    /
    -0.42
    ,
    -0.41
    ful
    -0.40
    POSITIVE LOGITS
    Geplaatst
    1.15
    GraphicsUnit
    0.94
    webElementXpaths
    0.94
     Roskov
    0.91
    帖最后由
    0.90
     betweenstory
    0.89
     ―――――
    0.88
    
    0.88
    elemField
    0.88
    onViewCreated
    0.87
    Activations Density 0.003%

    No Known Activations