© 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. 2073
    Prev
    Next
    INDEX
    Explanations

    ating

    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
     صوتيه
    -0.89
     Italij
    -0.75
     ainfi
    -0.75
    GEBURTSDATUM
    -0.73
    ContentAsync
    -0.73
    ImageContext
    -0.73
    mybatisplus
    -0.71
     doInBackground
    -0.69
     ſche
    -0.69
     houſe
    -0.69
    POSITIVE LOGITS
    .
    0.67
     is
    0.57
     has
    0.54
     .
    0.46
     uses
    0.42
     Auto
    0.41
     ""))
    0.41
     Series
    0.41
     believes
    0.41
     Gre
    0.40
    Activations Density 0.003%

    No Known Activations