© 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. 4-CLT-HP
    7. 4549
    Prev
    Next
    INDEX
    Explanations

    of

    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
    KommentareTeilen
    -0.70
    ########.
    -0.60
     dAtA
    -0.57
    consulté
    -0.52
    ///</
    -0.52
    BrowserModule
    -0.52
    OrNil
    -0.51
    awtextra
    -0.48
    Portály
    -0.48
    makeatother
    -0.48
    POSITIVE LOGITS
    ||}
    0.53
    Kjelder
    0.53
     Italijanski
    0.50
    ędzynarod
    0.48
    Rhestr
    0.48
     Holl
    0.47
    ktop
    0.47
    java
    0.46
    hoppers
    0.45
    넷
    0.45
    Activations Density 0.016%

    No Known Activations