© 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. 72589
    Prev
    Next
    INDEX
    Explanations

    —

    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
    fjspx
    -0.68
    TestingModule
    -0.65
    endpush
    -0.59
     cherchés
    -0.59
    ViewFeatures
    -0.57
     Final
    -0.57
     CanadaChoose
    -0.57
    third
    -0.56
     Signalez
    -0.56
     HasFactory
    -0.56
    POSITIVE LOGITS
    stdc
    0.52
    kesha
    0.51
    ClientSize
    0.51
     NKC
    0.47
    الإنجليزية
    0.46
    ヘル
    0.44
    ClientRect
    0.44
    ))=\
    0.44
     Frid
    0.42
    läufer
    0.42
    Activations Density 0.003%

    No Known Activations