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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76608
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act-logits · 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
     CreateTagHelper
    -0.81
    __':
    -0.76
    __':
    -0.76
     fubject
    -0.68
     WaitForSeconds
    -0.68
     MainAxisSize
    -0.67
    WebControls
    -0.66
     للاسماء
    -0.66
     يتيمه
    -0.64
    __":
    -0.62
    POSITIVE LOGITS
    aarrggbb
    0.59
    FormTagHelper
    0.48
     Cap
    0.44
    fjspx
    0.43
     Son
    0.41
    órm
    0.41
     son
    0.40
     el
    0.40
     cap
    0.40
    новниш
    0.40
    Activations Density 0.001%

    No Known Activations