© 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. 5-CLT-HP
    7. 1216
    Prev
    Next
    INDEX
    Explanations

    information, reports

    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
     hardly
    -0.90
     barely
    -0.90
     Hardly
    -0.89
     scarcely
    -0.76
     kaum
    -0.59
    +#+#
    -0.55
     nemmeno
    -0.52
     vagues
    -0.49
     cherchés
    -0.49
    Few
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.74
    WithIOException
    0.66
     disambiguazione
    0.65
    xodo
    0.60
    LabelTagHelper
    0.58
    ThroughAttribute
    0.57
    ńcu
    0.56
    ConverterFactory
    0.56
    Personendaten
    0.56
    ']>;
    0.54
    Activations Density 0.006%

    No Known Activations