© 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. 0-CLT-HP
    7. 41602
    Prev
    Next
    INDEX
    Explanations

    ink

    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
    WebVitals
    -0.82
     rospy
    -0.71
     melanin
    -0.67
     mauva
    -0.66
     Dormit
    -0.66
     himo
    -0.66
     Ruler
    -0.65
     الرياضيه
    -0.65
     seksual
    -0.64
    enterOuterAlt
    -0.64
    POSITIVE LOGITS
    ness
    0.71
    ly
    0.63
    nya
    0.59
    stone
    0.52
    shaft
    0.52
    raff
    0.49
    eries
    0.48
    leaved
    0.48
    man
    0.47
    ify
    0.47
    Activations Density 0.152%

    No Known Activations