© 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. 1096
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    melden
    -0.44
     richt
    -0.42
     initComponents
    -0.42
    קב
    -0.42
    aux
    -0.41
     sucedido
    -0.39
    Palabras
    -0.37
     conmigo
    -0.36
     in
    -0.36
    COHOL
    -0.36
    POSITIVE LOGITS
     كومونز
    0.88
     CreateTagHelper
    0.85
    OGND
    0.75
     оригіналу
    0.72
    Portail
    0.72
     nonUne
    0.70
    HideFlags
    0.68
     propOrder
    0.68
     understanding
    0.67
     of
    0.65
    Activations Density 0.003%

    No Known Activations