© 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. 5-CLT-HP
    7. 91255
    Prev
    Next
    INDEX
    Explanations

    impact

    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
    יתה
    -0.48
    <bos>
    -0.47
    imod
    -0.45
    diğim
    -0.43
    yorum
    -0.42
    彼女は
    -0.41
    WHEN
    -0.40
    diğinde
    -0.40
    差
    -0.39
    Контак
    -0.39
    POSITIVE LOGITS
    ècie
    0.68
     OFDb
    0.63
     homosexuality
    0.60
     utafitiHapana
    0.59
    adaptiveStyles
    0.57
     estekak
    0.57
    AnchorStyles
    0.56
    ThroughAttribute
    0.56
    وحة
    0.55
    ChildIndex
    0.55
    Activations Density 0.001%

    No Known Activations