© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6081
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Negative Logits
    RepeatedField
    -0.69
    ModelSerializer
    -0.63
    :✨
    -0.59
    GOTREF
    -0.58
    anguera
    -0.58
    pherd
    -0.55
    noticed
    -0.55
    InitStruct
    -0.54
     facilitates
    -0.54
    rafa
    -0.54
    POSITIVE LOGITS
     Use
    0.67
    }))
    0.61
    Use
    0.58
     Choose
    0.57
     use
    0.57
     choose
    0.54
     gebruik
    0.53
     chose
    0.49
     يتيمه
    0.49
    Choose
    0.48
    Activations Density 0.002%

    No Known Activations