© 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. 9454
    Prev
    Next
    INDEX
    Explanations

    Savage

    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
     myſelf
    -0.81
     themſelves
    -0.73
     himſelf
    -0.69
     poffible
    -0.68
     houſe
    -0.66
    ſelves
    -0.66
     Diſ
    -0.65
    neſs
    -0.63
    ſelf
    -0.62
     purpoſe
    -0.62
    POSITIVE LOGITS
    thâu
    0.62
    kháu
    0.54
    WriteTagHelper
    0.53
     Bioaccumulative
    0.50
     ivelany
    0.50
    Cyfeiriadau
    0.48
     >=",
    0.47
    Bioaccumulative
    0.47
     surla
    0.47
    Kanpo
    0.47
    Activations Density 0.016%

    No Known Activations