© 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. 0-CLT-HP
    7. 95054
    Prev
    Next
    INDEX
    Explanations

    technical topics

    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
     مشين
    -1.05
     HasFactory
    -0.99
    tvguidetime
    -0.97
    NameInMap
    -0.96
    oredCriteria
    -0.96
    adaptiveStyles
    -0.94
     protoimpl
    -0.94
     autorytatywna
    -0.93
    ViewFeatures
    -0.93
    EndGlobalSection
    -0.93
    POSITIVE LOGITS
    s
    0.76
    ся
    0.58
     imp
    0.50
     text
    0.48
     McIn
    0.47
    繹
    0.45
     R
    0.45
    j
    0.43
    ت
    0.43
    mack
    0.43
    Activations Density 0.052%

    No Known Activations