© 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. 5-CLT-HP
    7. 92865
    Prev
    Next
    INDEX
    Explanations

    say

    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
    WritableDatabase
    -0.55
     StringTokenizer
    -0.55
    AccessorTable
    -0.54
    AndEndTag
    -0.49
    рик
    -0.47
     propOrder
    -0.47
     layers
    -0.45
     stacks
    -0.45
     ApJ
    -0.44
    XmlAccessType
    -0.44
    POSITIVE LOGITS
     bäst
    0.58
     övers
    0.56
     vägen
    0.56
     mauvaises
    0.56
     behövs
    0.55
    شهاد
    0.54
     användas
    0.54
     pertes
    0.54
     malades
    0.53
    NewUrlParser
    0.53
    Activations Density 0.000%

    No Known Activations