© 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. 4-CLT-HP
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    4

    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
    <bos>
    -0.84
    loroethene
    -0.54
     dipende
    -0.45
     cúp
    -0.42
    čiau
    -0.42
    tfidf
    -0.42
     of
    -0.42
    ardini
    -0.41
    tze
    -0.40
    hara
    -0.40
    POSITIVE LOGITS
     onAnimation
    0.81
    GraphicsUnit
    0.77
     Roskov
    0.75
    +#+#
    0.75
    InjectAttribute
    0.74
    ⓧ
    0.72
     >=",
    0.69
    StoryboardSegue
    0.68
     CreateTagHelper
    0.68
     ISNI
    0.67
    Activations Density 0.023%

    No Known Activations