© 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. 42757
    Prev
    Next
    INDEX
    Explanations

    strengths, edu

    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
     strengths
    -1.77
     Strengths
    -1.24
    Strengths
    -1.02
    edu
    -0.76
    ngths
    -0.69
    STRENGTH
    -0.68
    stre
    -0.67
     STRENGTH
    -0.61
     Stär
    -0.57
    }*/
    -0.56
    POSITIVE LOGITS
    /*
    0.69
    URLException
    0.60
    +#+
    0.59
    consulté
    0.57
     NSCoder
    0.56
    ionario
    0.56
     gynhyrchwyd
    0.56
     Baillargeon
    0.56
    bundet
    0.55
    AccessLevel
    0.55
    Activations Density 0.098%

    No Known Activations