© 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. 42746
    Prev
    Next
    INDEX
    Explanations

    ultraviolet

    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
     Ultra
    -0.75
     ultra
    -0.73
    Ultra
    -0.68
     Peer
    -0.68
     peer
    -0.66
    nesses
    -0.66
    utnik
    -0.65
    Peer
    -0.64
    ultra
    -0.63
    ERS
    -0.57
    POSITIVE LOGITS
    featureID
    0.60
    posedge
    0.49
    Personendaten
    0.48
    Handlung
    0.47
    obec
    0.47
    theless
    0.45
    ally
    0.45
    GEBURTSDATUM
    0.45
    stretchr
    0.45
    KURZBESCHREIBUNG
    0.45
    Activations Density 1.571%

    No Known Activations