© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    reek

    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
    +#+#
    -0.72
    例句
    -0.60
     للمعارف
    -0.60
    fjspx
    -0.55
     unknownFields
    -0.55
     AppCompatTheme
    -0.55
    StoryboardSegue
    -0.54
     Bare
    -0.52
     Kung
    -0.52
     noDo
    -0.51
    POSITIVE LOGITS
     root
    0.63
     racines
    0.61
     cappuccio
    0.58
    roots
    0.56
     raíz
    0.56
     Root
    0.54
     sauvages
    0.53
     roots
    0.53
    root
    0.52
    Roots
    0.52
    Activations Density 0.000%

    No Known Activations