© 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. 4-CLT-HP
    7. 296
    Prev
    Next
    INDEX
    Explanations

    current

    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
     varandra
    -0.77
     feroit
    -0.75
     étoient
    -0.74
     auroit
    -0.71
    TestBed
    -0.69
     myſelf
    -0.69
     spesa
    -0.69
     Efq
    -0.69
     avoient
    -0.68
     Monfieur
    -0.67
    POSITIVE LOGITS
     and
    0.66
     times
    0.60
     (
    0.58
     day
    0.56
     &
    0.52
     generation
    0.51
     state
    0.49
     "
    0.49
    -
    0.48
     ad
    0.47
    Activations Density 0.007%

    No Known Activations