© 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. 41388
    Prev
    Next
    INDEX
    Explanations

    mod

    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
    mod
    -1.30
     mod
    -1.00
    Mod
    -1.00
     Mod
    -0.79
     overlapping
    -0.72
     overlap
    -0.65
     overlaps
    -0.64
    MOD
    -0.62
     intersect
    -0.60
     overlapped
    -0.59
    POSITIVE LOGITS
     متعلقه
    0.88
     ErrIntOverflow
    0.69
    LookAnd
    0.65
    sak
    0.65
    spesies
    0.64
     تضيفلها
    0.59
    etheless
    0.58
    eration
    0.57
     BoxFit
    0.57
    Panamoan
    0.56
    Activations Density 1.161%

    No Known Activations