© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    does

    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
    ⇑
    -0.60
    webElementGuid
    -0.59
     isInitialized
    -0.57
     gynnwys
    -0.55
    EndContext
    -0.52
    AccessorTable
    -0.51
     Normdatei
    -0.49
    InjectAttribute
    -0.49
    *************/
    -0.49
    ://
    -0.48
    POSITIVE LOGITS
     Majefty
    0.66
     himſelf
    0.64
     كومونز
    0.59
     Monfieur
    0.58
     myſelf
    0.58
     Theſe
    0.56
     whoſe
    0.56
     theſe
    0.55
    ungguhnya
    0.54
     leaſt
    0.53
    Activations Density 0.001%

    No Known Activations