© 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. 817
    Prev
    Next
    INDEX
    Explanations

    baby development

    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
    ETIES
    -0.50
    NOPQRST
    -0.50
    AnchorTagHelper
    -0.48
     Ceinture
    -0.47
    oa̍t
    -0.47
    IVEREF
    -0.46
    antan
    -0.46
    hadur
    -0.46
    mature
    -0.46
     Dead
    -0.46
    POSITIVE LOGITS
    mapreduce
    0.57
    خصة
    0.51
    afficheront
    0.50
    TintMode
    0.49
     încă
    0.48
    ’
    0.47
    labelledby
    0.47
    Geografi
    0.47
    urlopen
    0.47
    دانشنامهٔ
    0.46
    Activations Density 0.001%

    No Known Activations