© 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. 45040
    Prev
    Next
    INDEX
    Explanations

    of

    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
     of
    -0.56
    부터
    -0.49
    plik
    -0.48
     chimiques
    -0.48
     estabiliz
    -0.48
    agement
    -0.47
    CASCADE
    -0.47
    ebrow
    -0.47
     laikā
    -0.47
    Sø
    -0.46
    POSITIVE LOGITS
    ỡng
    0.77
     transférez
    0.70
     referenties
    0.69
     ProtoMessage
    0.66
    +#+#
    0.66
     himo
    0.63
     betweenstory
    0.62
     resourceCulture
    0.60
    #+#
    0.58
     ―――――
    0.58
    Activations Density 1.655%

    No Known Activations