© 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. 0-CLT-HP
    7. 44180
    Prev
    Next
    INDEX
    Explanations

    diamond

    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
     
    -0.59
    <eos>
    -0.51
     The
    -0.46
     his
    -0.45
     p
    -0.44
     the
    -0.44
     I
    -0.44
     f
    -0.44
     N
    -0.44
     reduction
    -0.44
    POSITIVE LOGITS
    NameInMap
    1.11
     Roskov
    1.09
    Geplaatst
    1.09
    WebVitals
    1.09
     defaultstate
    1.08
    StoryboardSegue
    1.03
    AccessorTable
    1.02
    GraphicsUnit
    1.01
     الرياضيه
    1.01
    RenderAtEndOf
    1.00
    Activations Density 0.211%

    No Known Activations