© 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. 1-CLT-HP
    7. 14116
    Prev
    Next
    INDEX
    Explanations

    and

    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
     متعلقه
    -0.73
     itſelf
    -0.66
     avoient
    -0.65
     betweenstory
    -0.65
    ToProps
    -0.65
     photolibrary
    -0.63
     فريبيس
    -0.61
     myſelf
    -0.61
     Reverso
    -0.61
     pngtree
    -0.60
    POSITIVE LOGITS
     fun
    0.69
    stdc
    0.57
     FUN
    0.54
     engaging
    0.54
     easy
    0.52
     vers
    0.51
    fun
    0.51
     sought
    0.50
     artistic
    0.50
     funny
    0.49
    Activations Density 0.020%

    No Known Activations