© 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. 20-CLT-HP
    7. 76101
    Prev
    Next
    INDEX
    Explanations

    Technical/code related texts

    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
    Pozri
    -0.64
     leveren
    -0.57
    migration
    -0.57
     levert
    -0.57
     registrazione
    -0.56
     exportación
    -0.54
     récupération
    -0.54
     câble
    -0.54
    APPS
    -0.53
     rospy
    -0.53
    POSITIVE LOGITS
     stepped
    0.59
    évaluateur
    0.56
     متعلقه
    0.56
     utafitiHapana
    0.54
    featureID
    0.54
    脚注の使い方
    0.51
    uxxxx
    0.51
     step
    0.50
     stepping
    0.50
     AssemblyVersion
    0.49
    Activations Density 0.000%

    No Known Activations