© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41809
    Prev
    Next
    INDEX
    Explanations

    omor

    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
    umon
    -0.84
    ImageContext
    -0.81
     NSCoder
    -0.78
     feroit
    -0.77
     Parrish
    -0.75
     étoit
    -0.74
     auroit
    -0.71
     frågan
    -0.68
     gouttes
    -0.68
    amarine
    -0.68
    POSITIVE LOGITS
     instrumental
    0.50
    <bos>
    0.49
    ()",
    0.46
    ”).
    0.46
     PublicKey
    0.46
    序
    0.45
    ill
    0.45
    mering
    0.45
     */;
    0.45
    "}";
    0.44
    Activations Density 0.055%

    No Known Activations