© 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. 42587
    Prev
    Next
    INDEX
    Explanations

    inv

    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
     Inv
    -0.60
    Inv
    -0.54
    #+#
    -0.52
    inv
    -0.50
    adaptiveStyles
    -0.48
    createCanvas
    -0.47
    verifyException
    -0.46
     MotionEvent
    -0.46
     couverture
    -0.45
    föl
    -0.45
    POSITIVE LOGITS
     unknownFields
    0.73
    findpost
    0.72
    IUrlHelper
    0.71
    InjectAttribute
    0.64
    ंदीखरीदारी
    0.64
    asable
    0.63
     contextLoads
    0.62
    writeFieldEnd
    0.62
    ſelf
    0.61
    ագրություններ
    0.60
    Activations Density 1.694%

    No Known Activations