© 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. 9302
    Prev
    Next
    INDEX
    Explanations

    Vertebrates and scientific texts

    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
    CodeAttribute
    -0.67
     Canvas
    -0.61
    帖最后由
    -0.59
    Canvas
    -0.52
    ngrx
    -0.52
    Rüyada
    -0.51
     Krakowie
    -0.50
     Wheatley
    -0.49
     Nuovo
    -0.49
    suchen
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.66
    DrawerToggle
    0.60
     FetchType
    0.57
    ScopeManager
    0.56
    numerusform
    0.55
    enumi
    0.54
     genoux
    0.54
     courants
    0.54
    ướt
    0.54
     Wicidata
    0.54
    Activations Density 0.012%

    No Known Activations