© 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. 0-CLT-HP
    7. 42456
    Prev
    Next
    INDEX
    Explanations

    don't

    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
     “
    -0.82
     don
    -0.77
    “
    -0.72
     doesn
    -0.68
     ‘
    -0.65
     isn
    -0.64
     didn
    -0.63
     Ivanov
    -0.62
     aren
    -0.62
     Don
    -0.61
    POSITIVE LOGITS
     BorderRadius
    0.68
    AnchorStyles
    0.56
    knapp
    0.53
     فريبيس
    0.52
    AndEndTag
    0.52
    ValueStyle
    0.51
     AssemblyCulture
    0.49
     '\\;'
    0.48
     Normdatei
    0.47
    ContentAlignment
    0.46
    Activations Density 0.128%

    No Known Activations