© 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. 94964
    Prev
    Next
    INDEX
    Explanations

    explanations or definitions

    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
    Przypisy
    -0.56
     Evidently
    -0.53
    ERN
    -0.52
     confirmed
    -0.49
     restored
    -0.48
     betreft
    -0.47
     alerted
    -0.47
    )|^{
    -0.47
    Trama
    -0.47
     ejected
    -0.47
    POSITIVE LOGITS
    +#+#
    0.73
    EndProject
    0.61
    dataclass
    0.59
    Rohy
    0.59
     nakalista
    0.59
    styleType
    0.56
     betweenstory
    0.56
    OGND
    0.56
    StoryboardSegue
    0.55
    AddTagHelper
    0.54
    Activations Density 0.000%

    No Known Activations