© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    pees

    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
     跳转至
    -0.59
     kasarigan
    -0.55
     oslo
    -0.53
    +#+#
    -0.52
    oa̍t
    -0.52
    +#+
    -0.50
    preduce
    -0.50
    StoryboardSegue
    -0.50
     χρόν
    -0.49
    keyColumn
    -0.49
    POSITIVE LOGITS
     AppColors
    0.57
     isNameExpr
    0.57
    msgTypes
    0.56
    modb
    0.52
    醐
    0.51
    Sklici
    0.50
     NavController
    0.49
     ToString
    0.48
    onFailure
    0.47
     &=&
    0.47
    Activations Density 0.000%

    No Known Activations