© 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. 43198
    Prev
    Next
    INDEX
    Explanations

    job titles

    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
     pleaſure
    -1.05
     purpoſe
    -1.05
     myſelf
    -1.03
     Monfieur
    -1.02
     Diſ
    -1.01
     ſtate
    -1.00
     faſt
    -0.97
     étoit
    -0.96
     itſelf
    -0.96
     Jefus
    -0.94
    POSITIVE LOGITS
    ']."
    0.59
    ']?>
    0.59
    --){
    0.58
     Gal
    0.58
     Bor
    0.55
    })(
    0.54
    "}\
    0.54
    '].'
    0.53
     der
    0.53
     cor
    0.53
    Activations Density 0.246%

    No Known Activations