© 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. 92419
    Prev
    Next
    INDEX
    Explanations

    Technical and mixed information

    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
    Personendaten
    -0.56
     newOwner
    -0.54
     étoient
    -0.53
     auroit
    -0.52
    WithIdentifier
    -0.52
     feroit
    -0.52
     Obispo
    -0.52
    kháu
    -0.52
    DBNull
    -0.51
     SafeMath
    -0.51
    POSITIVE LOGITS
    awtextra
    0.82
     come
    0.75
    IntoConstraints
    0.65
    come
    0.60
    RUPT
    0.57
     Come
    0.56
     kasarigan
    0.56
    chine
    0.53
     comes
    0.52
    gines
    0.52
    Activations Density 0.001%

    No Known Activations