© 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. 14590
    Prev
    Next
    INDEX
    Explanations

    enumer

    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
     correctes
    -0.75
    artifactId
    -0.67
     onCreateView
    -0.63
     cumin
    -0.61
    timewa
    -0.59
     Disse
    -0.58
     nakalista
    -0.57
     originalen
    -0.57
    Disse
    -0.56
    PerformLayout
    -0.56
    POSITIVE LOGITS
    verwijspagina
    0.63
    lus
    0.48
    ious
    0.46
    ous
    0.46
    Portail
    0.44
     brand
    0.44
    ier
    0.44
    Portale
    0.44
    used
    0.43
    bread
    0.43
    Activations Density 0.007%

    No Known Activations