© 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. 4-CLT-HP
    7. 478
    Prev
    Next
    INDEX
    Explanations

    permissions

    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
    ceus
    -0.55
     van
    -0.53
    ████
    -0.49
     ve
    -0.47
    '][$
    -0.45
    cestry
    -0.45
     Pag
    -0.45
     regional
    -0.44
     index
    -0.44
     complete
    -0.44
    POSITIVE LOGITS
     itſelf
    0.79
     canst
    0.73
     découver
    0.69
     myſelf
    0.66
     thyself
    0.66
     themſelves
    0.65
    脚注の使い方
    0.64
     chofe
    0.63
     poffible
    0.63
     Jefus
    0.61
    Activations Density 0.004%

    No Known Activations