© 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. 1-CLT-HP
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    research organizations and names

    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
    ThroughAttribute
    -0.63
     GetEnumerator
    -0.57
     Censo
    -0.56
    UnknownFieldSet
    -0.56
     Darling
    -0.54
    ollectionView
    -0.54
     AspNetCore
    -0.54
     Ober
    -0.54
    SharedCtor
    -0.54
    kloped
    -0.53
    POSITIVE LOGITS
    Identyfik
    0.57
    WriteBarrier
    0.52
    ]='\
    0.51
     nakalista
    0.50
     företag
    0.47
    NUMX
    0.46
     Unab
    0.45
    ஐ
    0.43
    Inc
    0.43
    ">'.$
    0.43
    Activations Density 0.027%

    No Known Activations