© 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. 2156
    Prev
    Next
    INDEX
    Explanations

    set

    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
     Taught
    -0.41
    oweit
    -0.41
    forth
    -0.40
    JAH
    -0.40
    seman
    -0.40
    ipzig
    -0.39
    teth
    -0.38
    øren
    -0.38
    ְ
    -0.38
    IContainer
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.93
    ########.
    0.76
    Portail
    0.72
    EDEFAULT
    0.70
    adpleegd
    0.70
    MLLoader
    0.68
    Contours
    0.66
    loroethene
    0.65
    !*\
    0.65
    Externí
    0.64
    Activations Density 0.001%

    No Known Activations