© 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. 1043
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ⓧ
    -1.02
     pinulongan
    -0.88
     незавершена
    -0.85
     createState
    -0.84
     kaarangay
    -0.74
     ModelExpression
    -0.73
    ettbewer
    -0.70
     Signalez
    -0.70
     EconPapers
    -0.70
     <=",
    -0.70
    POSITIVE LOGITS
    Even
    0.47
    )
    0.46
    ,
    0.44
    ;
    0.42
    \
    0.42
    Bahkan
    0.41
    ),
    0.41
    );
    0.41
    Last
    0.39
    Reviewed
    0.39
    Activations Density 0.004%

    No Known Activations