© 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. 72040
    Prev
    Next
    INDEX
    Explanations

    Code and technical 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
    rungsseite
    -0.76
     propOrder
    -0.71
    webElementXpaths
    -0.66
    fillType
    -0.65
    Personensuche
    -0.64
    featureID
    -0.63
    EndGlobalSection
    -0.63
    GEBURTSDATUM
    -0.60
    CloseOperation
    -0.59
    
    -0.58
    POSITIVE LOGITS
     Landis
    0.58
     Assim
    0.53
    oa̍t
    0.51
    HIGH
    0.48
     châssis
    0.48
     High
    0.47
    High
    0.47
    đu
    0.47
     dalamnya
    0.46
    Referencies
    0.46
    Activations Density 0.000%

    No Known Activations