© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94309
    Prev
    Next
    INDEX
    Explanations

    Explanations/justifications

    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
    EDEFAULT
    -0.82
     виправивши
    -0.80
    InstrumentedTest
    -0.74
    omiast
    -0.68
     الاطلاع
    -0.68
    IBOutlet
    -0.67
    LookAnd
    -0.66
     myſelf
    -0.66
    contentLoaded
    -0.65
    igshid
    -0.65
    POSITIVE LOGITS
     so
    0.69
     of
    0.69
    so
    0.58
     several
    0.56
     it
    0.54
     we
    0.54
     a
    0.52
     more
    0.50
    So
    0.49
     both
    0.47
    Activations Density 0.011%

    No Known Activations