© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40069
    Prev
    Next
    INDEX
    Explanations

    outcomes and consequences

    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
     result
    -1.38
    result
    -1.00
     résultat
    -0.79
     resultado
    -0.75
     resul
    -0.69
     Result
    -0.67
     consequence
    -0.66
    Filmographie
    -0.65
     outcome
    -0.65
     Ergebnis
    -0.62
    POSITIVE LOGITS
     betweenstory
    0.81
    omitempty
    0.63
    ########.
    0.63
    ReusableCell
    0.59
     viewDidLoad
    0.56
    ьаж
    0.55
     Wiktionnaire
    0.55
    TagMode
    0.54
    InitVars
    0.54
     awakeFromNib
    0.54
    Activations Density 0.038%

    No Known Activations