© 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. 20-CLT-HP
    7. 77094
    Prev
    Next
    INDEX
    Explanations

    certainty

    np_max-act-logits · 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
    ंदीखरीदारी
    -0.69
     cherchés
    -0.66
     jadx
    -0.64
    تقاوى
    -0.63
     tartalomajánló
    -0.62
    illère
    -0.61
    vician
    -0.61
     <<<<<<<<<<<<<<
    -0.59
    usercontent
    -0.59
    :+:
    -0.58
    POSITIVE LOGITS
     certain
    0.81
    Certain
    0.68
     sure
    0.66
    certain
    0.66
     Certain
    0.66
     CERTAIN
    0.60
     certaine
    0.57
     certa
    0.46
    Sure
    0.46
    undur
    0.44
    Activations Density 0.000%

    No Known Activations