© 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. 94812
    Prev
    Next
    INDEX
    Explanations

    joys, rewards

    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
     joys
    -0.84
     pleasures
    -0.79
     rewards
    -0.73
    ed
    -0.71
    InjectAttribute
    -0.70
     evils
    -0.69
     Jefus
    -0.68
    __':
    -0.63
    __":
    -0.63
     delights
    -0.62
    POSITIVE LOGITS
     كومونز
    0.62
    AddTagHelper
    0.57
    الإنجليزية
    0.55
    pecific
    0.52
     مرئيه
    0.52
    TRIBUN
    0.51
    omeness
    0.49
    porre
    0.49
    hoots
    0.48
    konferenz
    0.48
    Activations Density 0.639%

    No Known Activations