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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 100
    Prev
    Next
    INDEX
    Explanations

    jelly

    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
     jelly
    -0.66
     mustang
    -0.50
    DllImport
    -0.50
    <bos>
    -0.48
    wapV
    -0.47
    poque
    -0.47
    caire
    -0.46
     Mustang
    -0.46
     deposit
    -0.46
     band
    -0.46
    POSITIVE LOGITS
    +#+#
    0.67
    muerzo
    0.61
    igshid
    0.59
     springfox
    0.59
     élevées
    0.59
     heureuse
    0.58
     oreilles
    0.58
     touristes
    0.57
    featureID
    0.57
     lumineuse
    0.56
    Activations Density 0.032%

    No Known Activations