© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96101
    Prev
    Next
    INDEX
    Explanations

    biology

    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
     Vag
    -0.41
     Rogers
    -0.41
    Permalink
    -0.40
     دیکھیے
    -0.40
    chein
    -0.40
    عى
    -0.39
     sample
    -0.38
     bag
    -0.37
    Réalisation
    -0.37
     imagination
    -0.36
    POSITIVE LOGITS
    CrossRef
    0.77
    GOTREF
    0.71
    +#+#
    0.71
    MessageTagHelper
    0.70
    WriteBarrier
    0.64
     дописавши
    0.63
    fromCharCode
    0.61
     AssemblyTitle
    0.60
    Datuak
    0.60
    ))));
    0.60
    Activations Density 0.002%

    No Known Activations