© 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. 94934
    Prev
    Next
    INDEX
    Explanations

    halting

    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
     in
    -0.53
    IGraphics
    -0.51
     serving
    -0.47
     with
    -0.45
    findpost
    -0.44
     during
    -0.44
     proving
    -0.44
    ,
    -0.43
     providing
    -0.43
    .
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.77
    webElementXpaths
    0.75
    LookAnd
    0.74
     them
    0.73
     betweenstory
    0.69
     &___
    0.68
     kaarangay
    0.66
     мәкал
    0.65
    ]--;
    0.65
    脚注の使い方
    0.64
    Activations Density 0.002%

    No Known Activations