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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1070
    Prev
    Next
    INDEX
    Explanations

    Positive outcomes/improvements

    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
    posedge
    -0.84
     Roskov
    -0.77
     تضيفلها
    -0.73
     invokingState
    -0.69
     propOrder
    -0.69
     ProtoMessage
    -0.69
    YMMV
    -0.68
    Risultati
    -0.67
    transQ
    -0.66
    enterOuterAlt
    -0.66
    POSITIVE LOGITS
    AspNetCore
    0.46
    MockMvc
    0.43
    uzz
    0.42
    Inflater
    0.41
    TagHelper
    0.41
     Sobald
    0.40
     batteri
    0.40
    oning
    0.40
    vors
    0.39
    ondra
    0.39
    Activations Density 0.017%

    No Known Activations