© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1103
    Prev
    Next
    INDEX
    Explanations

    at

    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
     at
    -1.16
    at
    -0.67
    ,
    -0.58
     of
    -0.56
     
    -0.55
     in
    -0.53
     At
    -0.51
     -
    -0.50
    ide
    -0.48
     tại
    -0.48
    POSITIVE LOGITS
    +#+#
    1.42
     propOrder
    1.38
     المعيارى
    1.26
    RenderAtEndOf
    1.24
     itſelf
    1.17
     GenerationType
    1.13
    AddTagHelper
    1.11
     myſelf
    1.11
    Personendaten
    1.09
     transfieras
    1.07
    Activations Density 0.242%

    No Known Activations