© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77932
    Prev
    Next
    INDEX
    Explanations

    undertake

    np_max-act-logits · 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
    +#+#
    -0.74
    mappedBy
    -0.71
    :+:
    -0.71
     AssemblyCulture
    -0.65
     CreateTagHelper
    -0.64
    SequentialGroup
    -0.60
     Declare
    -0.59
    
    -0.58
    MarshalTo
    -0.56
     físicas
    -0.55
    POSITIVE LOGITS
     conversion
    0.50
    InitVars
    0.49
    UnsafeEnabled
    0.46
     PL
    0.45
     Idd
    0.45
    ppl
    0.44
     P
    0.44
     seats
    0.43
     subs
    0.43
     Cursor
    0.43
    Activations Density 0.001%

    No Known Activations