© 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. 91915
    Prev
    Next
    INDEX
    Explanations

    program

    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
    <bos>
    -0.81
     cherchés
    -0.79
    umumkan
    -0.77
    antaranya
    -0.72
    HostException
    -0.72
    })));
    -0.72
     createState
    -0.71
     للاسماء
    -0.70
     vendus
    -0.69
     snippetHide
    -0.67
    POSITIVE LOGITS
     capital
    0.56
    radiation
    0.51
     Capital
    0.50
     oxidation
    0.50
    رام
    0.50
    ELES
    0.50
    knecht
    0.49
     dosi
    0.49
    pheny
    0.49
    laß
    0.49
    Activations Density 0.194%

    No Known Activations