© 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. 20-CLT-HP
    7. 76808
    Prev
    Next
    INDEX
    Explanations

    code/data extraction

    np_max-act-logits · 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
    MigrationBuilder
    -1.07
    BeginContext
    -0.91
    MessageTagHelper
    -0.91
    rungsseite
    -0.91
    tvguidetime
    -0.90
    tagHelperRunner
    -0.88
     snippetHide
    -0.87
    AndEndTag
    -0.82
    
    -0.79
    PreferredItem
    -0.75
    POSITIVE LOGITS
     Kunde
    0.41
    Mitglied
    0.40
    out
    0.40
     jöv
    0.40
    IBUS
    0.39
    السكان
    0.38
     Ambiental
    0.37
     然
    0.37
     satunya
    0.37
    варь
    0.37
    Activations Density 0.000%

    No Known Activations