© 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. 0-CLT-HP
    7. 91144
    Prev
    Next
    INDEX
    Explanations

    overcoming problems

    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
    OGND
    -0.88
    DockStyle
    -0.79
     kasarigan
    -0.77
    Autoritní
    -0.77
     NSCoder
    -0.74
    Geplaatst
    -0.73
    
    -0.73
    ItemBackground
    -0.72
     متعلقه
    -0.69
     consultato
    -0.69
    POSITIVE LOGITS
    apa
    0.59
    Marshaller
    0.56
     nucléaire
    0.54
    ab
    0.54
     receiving
    0.54
    ac
    0.53
    ap
    0.53
    i
    0.53
    rec
    0.52
    u
    0.51
    Activations Density 0.095%

    No Known Activations