© 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. 94700
    Prev
    Next
    INDEX
    Explanations

    scientific analysis

    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
     mass
    -1.34
    mass
    -0.99
     measured
    -0.92
    measured
    -0.71
     voisins
    -0.70
    NUMX
    -0.70
     referred
    -0.69
     Mass
    -0.68
    ">//
    -0.68
     neighbor
    -0.66
    POSITIVE LOGITS
    ыгана
    0.47
    qk
    0.45
    own
    0.43
     gyhoeddwyd
    0.43
    śla
    0.42
     bismuth
    0.41
    Drop
    0.41
    Hard
    0.41
     to
    0.40
     cyto
    0.40
    Activations Density 0.342%

    No Known Activations