© 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. 91526
    Prev
    Next
    INDEX
    Explanations

    ax

    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
    __':
    -0.70
    脚注の使い方
    -0.63
    Portale
    -0.63
     BoxDecoration
    -0.61
    __':
    -0.60
    __":
    -0.59
    .*")]
    -0.59
    sizeCache
    -0.57
    PropTypes
    -0.56
    __":
    -0.55
    POSITIVE LOGITS
     CreateTagHelper
    0.68
     År
    0.57
     negroes
    0.55
    jeux
    0.55
     Jei
    0.54
    的问道
    0.54
     EXISTING
    0.53
    rivit
    0.52
     Kimball
    0.51
    ItemBackground
    0.51
    Activations Density 0.008%

    No Known Activations