© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93680
    Prev
    Next
    INDEX
    Explanations

    facets

    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
     facets
    -0.76
    érience
    -0.67
     facet
    -0.67
     discs
    -0.66
    الإنجليزية
    -0.62
     nakalista
    -0.60
    cores
    -0.60
     chromosomes
    -0.59
     applicator
    -0.59
     cores
    -0.58
    POSITIVE LOGITS
    CastException
    0.69
    ing
    0.60
     self
    0.53
     ddelweddau
    0.52
     Chwiliwch
    0.50
    ising
    0.50
    Personendaten
    0.49
    hem
    0.49
     sqlalchemy
    0.49
    Autoritní
    0.48
    Activations Density 1.797%

    No Known Activations