© 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. 72912
    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
    \{\\
    -0.77
    expandindo
    -0.64
    enumi
    -0.57
    хьтан
    -0.55
    tonsoft
    -0.54
     виправивши
    -0.53
    quelize
    -0.52
    protoc
    -0.51
    findpost
    -0.51
     UserController
    -0.50
    POSITIVE LOGITS
     pageContext
    0.47
    IInterface
    0.46
    NOPQRST
    0.45
    rawDesc
    0.45
    anInt
    0.44
    hkan
    0.43
     acompañada
    0.42
    はじめに
    0.41
     armp
    0.41
    rifuge
    0.41
    Activations Density 0.002%

    No Known Activations