© 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. 0-CLT-HP
    4. 1226
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
     Y
    -1.05
     
    -0.81
     of
    -0.79
     (
    -0.72
    ,
    -0.68
     to
    -0.66
    -
    -0.66
     y
    -0.65
    Y
    -0.63
     and
    -0.62
    POSITIVE LOGITS
     betweenstory
    1.59
    StructEnd
    1.39
     itſelf
    1.38
     تضيفلها
    1.33
    Personendaten
    1.33
     myſelf
    1.30
     ―――――
    1.29
     doubtnut
    1.28
     photolibrary
    1.26
     Theſe
    1.26
    Activations Density 0.762%

    No Known Activations