© 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. 43022
    Prev
    Next
    INDEX
    Explanations

    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
    iffance
    -0.92
    PSON
    -0.80
    æus
    -0.78
    berton
    -0.76
    quisite
    -0.76
    AndroidJUnit
    -0.75
    enzuela
    -0.74
    BibitemShut
    -0.74
    AMENTO
    -0.73
     résister
    -0.73
    POSITIVE LOGITS
    ed
    0.62
    ad
    0.60
    ii
    0.60
    ik
    0.59
     Protestantism
    0.59
    ite
    0.59
    ec
    0.58
    im
    0.58
    ne
    0.57
    ian
    0.57
    Activations Density 0.122%

    No Known Activations