© 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. 0-CLT-HP
    7. 94121
    Prev
    Next
    INDEX
    Explanations

    Fort Worth, Texas/Facts

    np_max-act · gemini-2.0-flash

    Worth Method used: 1 — MAX_ACTIVATING_TOKENS are the same token, so "Worth"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Worth
    -1.00
    Worth
    -0.64
     WORTH
    -0.56
     “
    -0.53
     صوتيه
    -0.52
     
    -0.50
     su
    -0.48
     for
    -0.48
     zu
    -0.48
     "
    -0.45
    POSITIVE LOGITS
     itſelf
    0.94
     Efq
    0.84
     Jefus
    0.82
     bezeichneter
    0.80
     Theſe
    0.78
     becauſe
    0.77
    enumi
    0.76
     Monfieur
    0.76
     myſelf
    0.74
     Eſ
    0.73
    Activations Density 1.479%

    No Known Activations