© 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. 1-CLT-HP
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    failure

    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
    gaon
    -0.57
     Gatwick
    -0.47
    కా
    -0.47
    ıntı
    -0.47
    🏼
    -0.46
     réjou
    -0.45
    dotta
    -0.45
     kalın
    -0.45
    🏻
    -0.45
     chod
    -0.44
    POSITIVE LOGITS
    IntoConstraints
    0.75
    FunctionFlags
    0.71
    ="@+
    0.69
    DockStyle
    0.66
    WithIOException
    0.65
    Portály
    0.65
     pinulongan
    0.65
    expandindo
    0.62
     يتيمه
    0.62
     beginnetje
    0.62
    Activations Density 0.286%

    No Known Activations