© 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. 45060
    Prev
    Next
    INDEX
    Explanations

    do

    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
    RectangleBorder
    -1.24
    Personensuche
    -1.21
     BoxFit
    -1.16
     myſelf
    -1.16
     itſelf
    -1.13
     Theſe
    -1.08
     InputDecoration
    -1.06
     ―――――
    -1.05
     $_"
    -1.03
     betweenstory
    -1.03
    POSITIVE LOGITS
     not
    1.27
     
    0.95
     the
    0.91
    ,
    0.91
    .
    0.89
    ↵↵
    0.85
     NOT
    0.79
    :
    0.78
     a
    0.77
     also
    0.75
    Activations Density 0.071%

    No Known Activations