© 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. 20-CLT-HP
    7. 77660
    Prev
    Next
    INDEX
    Explanations

    miscellaneous topics

    np_max-act-logits · 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
    Portale
    -0.56
    iibo
    -0.53
    ruptedException
    -0.53
     IntelliJ
    -0.52
    rangea
    -0.51
    seiko
    -0.50
    tonode
    -0.50
    laston
    -0.50
    webElementGuid
    -0.49
    bandcamp
    -0.48
    POSITIVE LOGITS
     appelez
    0.52
    rungsseite
    0.51
    ValueStyle
    0.50
     gold
    0.49
    endphp
    0.48
    webElementXpaths
    0.47
    utica
    0.47
    Fr
    0.47
     fran
    0.47
    utsch
    0.47
    Activations Density 0.000%

    No Known Activations