© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    Descriptions

    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
     >=",
    -0.79
     insuffisamment
    -0.76
     AssemblyTitle
    -0.73
    Geplaatst
    -0.73
     autorytatywna
    -0.65
     مواليد
    -0.63
    exitRule
    -0.62
     للاسماء
    -0.61
    Życiorys
    -0.61
    Personensuche
    -0.60
    POSITIVE LOGITS
     catch
    0.69
     caveat
    0.56
    quec
    0.50
    pions
    0.47
    ylvan
    0.47
    ುತ್ತ
    0.46
    WriteAttribute
    0.46
    WithFormat
    0.45
     asterisk
    0.45
    ='$
    0.44
    Activations Density 0.001%

    No Known Activations