© 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. 92356
    Prev
    Next
    INDEX
    Explanations

    Opinions and editorials

    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
     betweenstory
    -0.91
    LookAnd
    -0.87
    Rujuakan
    -0.81
    CloseOperation
    -0.80
    ftagPool
    -0.77
    Personendaten
    -0.77
    enterOuterAlt
    -0.76
     незавершена
    -0.74
    parsedMessage
    -0.74
    kháu
    -0.72
    POSITIVE LOGITS
     especias
    0.48
     ngoại
    0.47
     démarrer
    0.47
    落
    0.46
     Academy
    0.46
     merve
    0.45
    gak
    0.45
     préc
    0.43
     sospe
    0.43
     femmin
    0.42
    Activations Density 0.004%

    No Known Activations