© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78244
    Prev
    Next
    INDEX
    Explanations

    potassium

    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
    Negative Logits
    LLocation
    -0.75
    ChildScrollView
    -0.70
     Hanne
    -0.69
    ContentLoaded
    -0.69
    EditorBrowsable
    -0.68
    CppMethod
    -0.66
     unknownFields
    -0.66
     InputDecoration
    -0.64
    iotensin
    -0.63
    FontOfSize
    -0.63
    POSITIVE LOGITS
     perm
    0.41
     sorti
    0.39
     Spar
    0.39
    timm
    0.38
    Spar
    0.37
    لوم
    0.37
     kertoo
    0.37
     avulla
    0.37
    gadas
    0.36
     pytania
    0.36
    Activations Density 0.002%

    No Known Activations