© 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. 1-CLT-HP
    7. 10023
    Prev
    Next
    INDEX
    Explanations

    parap

    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
     parap
    -0.64
     secretions
    -0.63
     cheese
    -0.60
    oma
    -0.60
     Cheese
    -0.50
     contents
    -0.50
    pyp
    -0.49
     AppComponent
    -0.48
     secretion
    -0.47
    ce
    -0.47
    POSITIVE LOGITS
     auroit
    0.68
     parete
    0.67
    Encyklopedia
    0.67
     edelstahl
    0.66
     avoient
    0.66
     feroit
    0.65
     plufieurs
    0.65
     pauv
    0.64
     bonté
    0.64
     étoit
    0.63
    Activations Density 0.007%

    No Known Activations