© 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. 14770
    Prev
    Next
    INDEX
    Explanations

    guidelines

    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
    AndEndTag
    -0.72
    photobucket
    -0.68
    awtextra
    -0.65
    kheim
    -0.63
    demort
    -0.60
    AxisAlignment
    -0.59
    GEBURTSDATUM
    -0.56
    Newswire
    -0.52
    modelBuilder
    -0.52
    AddHtmlAttribute
    -0.52
    POSITIVE LOGITS
     utafitiHapana
    0.52
     Theſe
    0.48
    richment
    0.47
     himſelf
    0.47
    insegna
    0.47
    cellence
    0.46
     on
    0.46
     Leal
    0.45
    testify
    0.45
     Tind
    0.44
    Activations Density 0.008%

    No Known Activations