© 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. 71912
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    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
     nakalista
    -0.87
    SequentialGroup
    -0.79
    Diweddarwch
    -0.75
    IsContent
    -0.73
    DebuggerNonUser
    -0.71
    AlterField
    -0.67
     Exactos
    -0.66
    rawDesc
    -0.66
    StoreMessageInfo
    -0.62
     asiatique
    -0.62
    POSITIVE LOGITS
    SceneManagement
    0.42
    giv
    0.38
    istoitu
    0.36
    rn
    0.35
    de
    0.33
    setPage
    0.33
    ٰ
    0.33
    SPATH
    0.32
    ona
    0.32
    baya
    0.32
    Activations Density 0.000%

    No Known Activations