© 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. 5328
    Prev
    Next
    INDEX
    Explanations

    action

    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
    GOTREF
    -0.57
     GenerationType
    -0.56
     JUGA
    -0.53
    elock
    -0.49
    aarrggbb
    -0.46
    HtmlAttribute
    -0.46
    schaft
    -0.46
     getItemId
    -0.46
     köl
    -0.46
    ThemeOverlay
    -0.45
    POSITIVE LOGITS
    arcoma
    0.57
    BufferException
    0.54
    फल
    0.54
    Filmografie
    0.54
    GEBURTS
    0.53
     compi
    0.52
     typelib
    0.52
    te
    0.52
    ons
    0.49
    Tazama
    0.48
    Activations Density 0.022%

    No Known Activations