© 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. 5-CLT-HP
    7. 92407
    Prev
    Next
    INDEX
    Explanations

    asim

    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
     Girls
    -0.51
     مشين
    -0.50
     girl
    -0.49
    apar
    -0.49
     girls
    -0.49
     Girl
    -0.49
     gadis
    -0.46
     gril
    -0.46
     boys
    -0.46
     unidade
    -0.45
    POSITIVE LOGITS
     ddelweddau
    0.66
     estekak
    0.64
     ComVisible
    0.61
    ,:);
    0.60
    tawesome
    0.58
    rawDesc
    0.57
    orghini
    0.56
    openzeppelin
    0.56
     Audiodateien
    0.55
    اریخ
    0.55
    Activations Density 0.002%

    No Known Activations