© 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. 94449
    Prev
    Next
    INDEX
    Explanations

    engines and machinery

    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
     photolibrary
    -1.37
     $_(
    -1.27
     myſelf
    -1.26
     crdi
    -1.25
     betweenstory
    -1.24
     itſelf
    -1.24
    ^(@)
    -1.23
     ་་
    -1.23
     AssemblyTitle
    -1.20
     doubtnut
    -1.20
    POSITIVE LOGITS
    er
    1.07
     (
    0.93
    ers
    0.90
     for
    0.88
    ,
    0.88
     
    0.86
    .
    0.85
    set
    0.85
    st
    0.84
    sp
    0.82
    Activations Density 0.043%

    No Known Activations