© 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. 5-CLT-HP
    4. 985
    Prev
    Next
    INDEX
    Explanations

    webpages

    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
     pitié
    -0.55
    StoryboardSegue
    -0.52
     solidarité
    -0.50
     gloire
    -0.50
    őd
    -0.49
     mulia
    -0.49
     AssemblyProduct
    -0.48
     moindre
    -0.47
     élégante
    -0.47
     élégant
    -0.46
    POSITIVE LOGITS
     esternos
    0.56
     "¿
    0.55
    =$?
    0.55
     Hear
    0.53
    :-
    0.52
    脚注の使い方
    0.51
    :";
    0.51
    :​
    0.51
    GGLE
    0.50
    ductory
    0.50
    Activations Density 0.001%

    No Known Activations