© 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. 5-CLT-HP
    7. 5016
    Prev
    Next
    INDEX
    Explanations

    hack

    np_max-act · 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
    Portale
    -0.62
    Blurb
    -0.57
    inari
    -0.46
    metido
    -0.45
     Sentin
    -0.43
     décret
    -0.42
     toepassing
    -0.40
     Mores
    -0.40
     saiba
    -0.40
     lähe
    -0.39
    POSITIVE LOGITS
     ligiloj
    0.66
     autorytatywna
    0.62
    SequentialGroup
    0.61
     Baillargeon
    0.59
    atoga
    0.57
    aday
    0.57
     ihop
    0.57
    psack
    0.56
    ArgsConstructor
    0.55
    ajs
    0.55
    Activations Density 0.003%

    No Known Activations