© 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. 91926
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
     resistenza
    -0.61
     pagare
    -0.60
    .—
    -0.57
     cielos
    -0.56
     mêmes
    -0.54
     rä
    -0.53
     perdere
    -0.52
     méthodes
    -0.52
     resistência
    -0.52
     ouvriers
    -0.52
    POSITIVE LOGITS
    GraphicsUnit
    0.68
    URLException
    0.62
    脚注の使い方
    0.60
    (!__
    0.59
    ArgsConstructor
    0.59
    WindowListener
    0.59
     invokingState
    0.57
    BufferException
    0.57
    ỡng
    0.55
    ContentAsync
    0.54
    Activations Density 0.004%

    No Known Activations