© 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. 39832
    Prev
    Next
    INDEX
    Explanations

    Socrates

    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
     متعلقه
    -0.70
     bypassed
    -0.66
     Socrates
    -0.65
    posedge
    -0.64
     AttributeSet
    -0.64
    avond
    -0.64
     Parthen
    -0.64
     Bantu
    -0.63
     Bellas
    -0.63
    able
    -0.63
    POSITIVE LOGITS
    ing
    0.65
    ING
    0.50
    akhstan
    0.46
    styleable
    0.46
    inges
    0.45
    IZON
    0.44
    getLastName
    0.44
    Données
    0.43
    τός
    0.43
     noDo
    0.42
    Activations Density 0.038%

    No Known Activations