© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 1026
    Prev
    Next
    INDEX
    Explanations

    berg

    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
     kerosene
    -0.70
    routeProvider
    -0.53
    BERG
    -0.53
    UGAL
    -0.48
    IsMutable
    -0.47
     MIS
    -0.47
    Assured
    -0.47
    OrBuilder
    -0.47
    +#+
    -0.47
    berg
    -0.46
    POSITIVE LOGITS
    es
    0.66
    saraba
    0.57
    se
    0.55
     placenta
    0.53
    on
    0.53
    mu
    0.52
    MULT
    0.52
     reactants
    0.52
    jsonwebtoken
    0.52
    vants
    0.52
    Activations Density 0.027%

    No Known Activations