© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94814
    Prev
    Next
    INDEX
    Explanations

    Code/documentation snippets

    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
     More
    -0.69
    #+#
    -0.69
     To
    -0.63
     Such
    -0.57
     Much
    -0.57
     pédagogique
    -0.57
     становника
    -0.57
     extérieures
    -0.57
    zahlt
    -0.57
     Less
    -0.56
    POSITIVE LOGITS
     betweenstory
    0.63
    XmlAccessType
    0.58
    matchCondition
    0.50
    fraid
    0.50
    ocratic
    0.47
    Hozzáférés
    0.47
     voluntary
    0.46
     triple
    0.46
     rigor
    0.46
     rationale
    0.45
    Activations Density 0.001%

    No Known Activations