© 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. 93063
    Prev
    Next
    INDEX
    Explanations

    possible

    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
     feasible
    -1.35
    reasonable
    -1.25
     raisonnable
    -1.23
     reasonable
    -1.22
     accesibles
    -1.20
     manageable
    -1.20
     compréhen
    -1.20
     démocr
    -1.18
     workable
    -1.17
     practicable
    -1.16
    POSITIVE LOGITS
     amount
    0.60
     use
    0.58
     job
    0.58
     art
    0.57
     work
    0.52
    ,
    0.52
     person
    0.52
     je
    0.50
     and
    0.50
     amounts
    0.49
    Activations Density 0.045%

    No Known Activations