© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91414
    Prev
    Next
    INDEX
    Explanations

    names/places

    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
     estekak
    -0.84
    Personendaten
    -0.79
     nakalista
    -0.77
     propOrder
    -0.76
    MLLoader
    -0.75
     linkovi
    -0.68
    XmlEnum
    -0.66
    PRNewswire
    -0.66
     kasarigan
    -0.63
    Rhestr
    -0.62
    POSITIVE LOGITS
     High
    0.96
    High
    0.76
     high
    0.73
     HIGH
    0.68
    high
    0.62
    HIGH
    0.56
     HS
    0.53
    高
    0.52
     高
    0.50
     Height
    0.46
    Activations Density 0.009%

    No Known Activations