© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74478
    Prev
    Next
    INDEX
    Explanations

    Code and technical snippets

    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
     الرياضيه
    -0.64
    HideFlags
    -0.61
     povezave
    -0.54
    Viited
    -0.51
     ComVisible
    -0.47
     ModelExpression
    -0.47
    Jeografia
    -0.45
     Bioaccumulative
    -0.44
    AnimationsModule
    -0.44
     Chwiliwch
    -0.44
    POSITIVE LOGITS
     Réponses
    0.65
     myſelf
    0.60
    URLException
    0.57
     itſelf
    0.54
     nine
    0.53
    UnknownFields
    0.52
     capt
    0.52
     purpoſe
    0.52
     Leader
    0.51
     ſeveral
    0.50
    Activations Density 0.000%

    No Known Activations