© 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. 20-CLT-HP
    7. 77760
    Prev
    Next
    INDEX
    Explanations

    technical/medical documents

    np_max-act-logits · 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
    Tikang
    -0.74
     оригіналу
    -0.69
     تضيفلها
    -0.65
    EndGlobalSection
    -0.64
    الإنجليزية
    -0.63
    SqlSession
    -0.52
     Zola
    -0.52
    ölkerung
    -0.52
    ApiModelProperty
    -0.52
     Britann
    -0.51
    POSITIVE LOGITS
    tiv
    0.53
    ypeł
    0.50
    schmidt
    0.50
    TYPED
    0.49
     Ge
    0.49
    XtraReports
    0.48
    pose
    0.46
    feest
    0.46
    orr
    0.45
    ët
    0.44
    Activations Density 0.001%

    No Known Activations