© 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. 0-CLT-HP
    7. 93665
    Prev
    Next
    INDEX
    Explanations

    vacuum

    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
     Milk
    -1.50
     disambiguazione
    -1.48
     myſelf
    -1.48
     milk
    -1.44
     ainfi
    -1.40
    Milk
    -1.38
     feroit
    -1.34
     MILK
    -1.34
     avoient
    -1.33
     auroit
    -1.32
    POSITIVE LOGITS
    -
    0.84
    ,
    0.79
     in
    0.76
     (
    0.74
    .
    0.73
     or
    0.71
    /
    0.70
     
    0.67
     l
    0.67
     is
    0.66
    Activations Density 0.067%

    No Known Activations