Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91355
    Prev
    Next
    INDEX
    Explanations

    kinder

    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
    ^(@)
    -0.90
     myſelf
    -0.88
     uſed
    -0.84
    @[+][
    -0.82
     الحره
    -0.82
     Monfieur
    -0.82
    TemporalType
    -0.82
     doubtnut
    -0.82
     poffible
    -0.81
    httphttps
    -0.81
    POSITIVE LOGITS
    ly
    1.09
    es
    0.72
    ments
    0.65
    s
    0.63
    als
    0.57
    LY
    0.57
    the
    0.54
    mente
    0.52
     
    0.50
    less
    0.49
    Activations Density 0.112%

    No Known Activations