© 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. 14974
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     raiſ
    -1.00
     purpoſe
    -1.00
     uſed
    -0.97
     myſelf
    -0.92
     uſe
    -0.90
     ―――――
    -0.90
     itſelf
    -0.90
     ſy
    -0.88
     iſt
    -0.88
     CreateTagHelper
    -0.88
    POSITIVE LOGITS
    linalg
    0.43
    euler
    0.39
    argmax
    0.37
    recursive
    0.36
    linspace
    0.35
    matmul
    0.34
    ,
    0.34
     Mas
    0.34
    allclose
    0.34
    <code>
    0.33
    Activations Density 0.105%

    No Known Activations