© 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. 72918
    Prev
    Next
    INDEX
    Explanations

    technical/informative text

    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
    Geplaatst
    -0.73
     Describes
    -0.69
     Cæsar
    -0.66
    SharedDtor
    -0.66
    Sucesor
    -0.66
     berätt
    -0.65
    Statements
    -0.65
    Says
    -0.64
     فريبيس
    -0.64
    statements
    -0.63
    POSITIVE LOGITS
     id
    0.50
     Tad
    0.48
     Id
    0.47
     mark
    0.46
     call
    0.45
    terung
    0.44
     name
    0.43
     ID
    0.43
     Mark
    0.42
    httphttps
    0.41
    Activations Density 0.000%

    No Known Activations