© 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. 0-CLT-HP
    7. 93780
    Prev
    Next
    INDEX
    Explanations

    conclusion/end

    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
     careers
    -1.46
     career
    -1.44
    career
    -1.35
     abandon
    -1.15
     carrière
    -1.13
     Abandon
    -1.12
    Career
    -1.10
     Career
    -1.09
     abandoned
    -1.06
    careers
    -1.05
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.53
    ally
    0.53
    ly
    0.49
     الحره
    0.48
    Lähteet
    0.45
     LEYENDO
    0.44
     spreads
    0.43
     onCreateView
    0.43
     animating
    0.43
     Wickham
    0.42
    Activations Density 0.090%

    No Known Activations