© 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. 4-CLT-HP
    7. 3090
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Bellini
    -0.53
     Efq
    -0.53
    providedIn
    -0.52
     organising
    -0.52
    ::-
    -0.51
    PerformLayout
    -0.50
     băr
    -0.50
     altrett
    -0.49
     matched
    -0.48
     animada
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.72
    WebVitals
    0.71
     Normdatei
    0.70
    ValueStyle
    0.62
    AddHtmlAttribute
    0.59
    MENAFN
    0.59
    Personendaten
    0.58
    醐
    0.57
    WithIOException
    0.56
     continúas
    0.54
    Activations Density 0.003%

    No Known Activations