© 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. 1-CLT-HP
    7. 14484
    Prev
    Next
    INDEX
    Explanations

    type

    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
     المعيارى
    -0.88
    sidemargin
    -0.86
    complexContent
    -0.85
    bootstrapcdn
    -0.73
     &___
    -0.71
     resourceCulture
    -0.70
     protoimpl
    -0.70
    PreferredItem
    -0.68
    astify
    -0.68
    Попис
    -0.67
    POSITIVE LOGITS
     jury
    0.39
     дописавши
    0.39
    bap
    0.38
     cade
    0.38
    /**
    0.37
    <bos>
    0.37
     """
    0.37
    )(((
    0.37
    glers
    0.36
     internazionali
    0.36
    Activations Density 0.032%

    No Known Activations