Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39089
    Prev
    Next
    INDEX
    Explanations

    useful usable

    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
    useful
    -1.65
     useful
    -1.55
     Useful
    -1.30
     usable
    -1.21
     útil
    -1.14
     utile
    -1.14
    Useful
    -1.13
     útiles
    -1.05
     utiles
    -1.00
    usable
    -0.96
    POSITIVE LOGITS
    s
    0.90
    ness
    0.68
     propOrder
    0.59
    ity
    0.57
    ance
    0.54
    itarian
    0.54
    er
    0.52
    ers
    0.52
    ities
    0.52
     unknownFields
    0.52
    Activations Density 0.108%

    No Known Activations