© 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. 77198
    Prev
    Next
    INDEX
    Explanations

    way halfway

    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
     leçon
    -0.66
    ніципалі
    -0.66
    ContentAlignment
    -0.62
     ویکی‌پدیا
    -0.62
    andExpect
    -0.60
    FlatAppearance
    -0.60
     nemico
    -0.60
    DoubleQuotes
    -0.59
     dignité
    -0.59
     imageNamed
    -0.57
    POSITIVE LOGITS
     through
    0.59
     thru
    0.47
    through
    0.47
     través
    0.47
     Through
    0.45
     thor
    0.44
    Through
    0.43
     >=",
    0.42
     via
    0.42
    alyptus
    0.42
    Activations Density 0.001%

    No Known Activations