© 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. 0-CLT-HP
    7. 40042
    Prev
    Next
    INDEX
    Explanations

    summer

    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
     summer
    -2.28
    summer
    -2.17
     Summer
    -2.14
    Summer
    -2.08
     SUMMER
    -1.91
     zomer
    -1.70
    SUMMER
    -1.69
     verano
    -1.63
     summertime
    -1.63
     sommar
    -1.33
    POSITIVE LOGITS
     inversion
    0.48
     bleeding
    0.43
    nene
    0.42
    linge
    0.41
    es
    0.41
    LOGY
    0.40
    ayette
    0.40
    Gare
    0.40
     dwelling
    0.40
     genome
    0.39
    Activations Density 0.102%

    No Known Activations