© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    Coordinates or values

    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
     pageContext
    -0.49
     WS
    -0.49
     Arta
    -0.47
     EW
    -0.46
    Ler
    -0.46
    xia
    -0.45
     YM
    -0.45
     when
    -0.45
    ấc
    -0.45
    RTSC
    -0.45
    POSITIVE LOGITS
    GraphicsUnit
    0.81
     EconPapers
    0.70
    MockBean
    0.55
     незавершена
    0.54
    ">//
    0.53
    quelize
    0.51
    cedido
    0.50
    archiviato
    0.50
     EnglishChoose
    0.50
    issauga
    0.49
    Activations Density 0.027%

    No Known Activations