Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73847
    Prev
    Next
    INDEX
    Explanations

    compact

    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
     BoxDecoration
    -0.75
    abstractmethod
    -0.64
    aarrggbb
    -0.63
     propOrder
    -0.58
    skjaer
    -0.55
     Personne
    -0.54
    multer
    -0.54
    FunctionFlags
    -0.53
     InputDecoration
    -0.53
    pyx
    -0.51
    POSITIVE LOGITS
     arabe
    0.49
    aviar
    0.47
    Brief
    0.45
    itres
    0.45
    èces
    0.45
    brief
    0.44
    asantry
    0.43
     Brief
    0.43
    اریخ
    0.42
     Beige
    0.42
    Activations Density 0.001%

    No Known Activations