© 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. 5-CLT-HP
    7. 5420
    Prev
    Next
    INDEX
    Explanations

    quantity/negation words

    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
     nahilalakip
    -0.76
    IntoConstraints
    -0.74
    AndEndTag
    -0.67
    jspx
    -0.67
     Exacts
    -0.66
    InputBorder
    -0.65
     []:
    -0.63
    ConstraintMaker
    -0.61
     AssemblyCulture
    -0.60
    +#+#
    -0.58
    POSITIVE LOGITS
     child
    0.61
     huge
    0.55
    .~(\
    0.54
    alnız
    0.52
     community
    0.52
     trader
    0.51
     chain
    0.51
     chains
    0.50
     further
    0.50
     great
    0.50
    Activations Density 0.001%

    No Known Activations