© 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. 45170
    Prev
    Next
    INDEX
    Explanations

    Australian locations

    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
    ſelf
    -0.97
     betweenstory
    -0.96
     Roskov
    -0.96
    tagHelperRunner
    -0.92
    ########.
    -0.92
     itſelf
    -0.90
     myſelf
    -0.90
     protoimpl
    -0.89
    NewUrlParser
    -0.87
     doubtnut
    -0.85
    POSITIVE LOGITS
    ist
    0.72
    in
    0.60
    ists
    0.59
    L
    0.56
     
    0.55
     L
    0.55
    ed
    0.54
    am
    0.54
    l
    0.53
    is
    0.52
    Activations Density 0.218%

    No Known Activations