© 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. 1-CLT-HP
    7. 14175
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    UserScript
    -0.68
    unk
    -0.65
    unking
    -0.50
    <>("
    -0.49
    +");
    -0.49
    hObject
    -0.48
     Endocrinol
    -0.48
    ighbor
    -0.48
    горь
    -0.47
     unk
    -0.46
    POSITIVE LOGITS
    PreferredItem
    0.72
     BoxFit
    0.61
    AndEndTag
    0.58
     bağlantılar
    0.57
    出版年
    0.56
    JsonInclude
    0.54
     Baillargeon
    0.54
    γμα
    0.54
     Lijst
    0.52
    imed
    0.51
    Activations Density 0.154%

    No Known Activations