© 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. 0-CLT-HP
    7. 94376
    Prev
    Next
    INDEX
    Explanations

    Jewelry and names

    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
    CodeAttribute
    -0.89
     GenerationType
    -0.81
    expandindo
    -0.80
    TargetException
    -0.69
     jewel
    -0.69
    StoryboardSegue
    -0.67
     jewels
    -0.65
     widow
    -0.64
    hwar
    -0.64
     Jewel
    -0.63
    POSITIVE LOGITS
    er
    0.66
    es
    0.62
    ing
    0.58
     pouvoir
    0.51
     poder
    0.50
    Eksteraj
    0.47
    таж
    0.47
     sharing
    0.46
    share
    0.46
    led
    0.45
    Activations Density 0.039%

    No Known Activations