© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93664
    Prev
    Next
    INDEX
    Explanations

    Jumper

    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
    <bos>
    -0.66
     igång
    -0.65
     brukt
    -0.63
     betale
    -0.60
     nö
    -0.59
     bär
    -0.59
     brukes
    -0.57
     igjen
    -0.56
     gjø
    -0.56
     finnas
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.98
    providedIn
    0.89
     AssemblyTitle
    0.83
    +#+#
    0.82
    StoryboardSegue
    0.80
     tartalomajánló
    0.80
     Normdatei
    0.77
     متعلقه
    0.75
     armb
    0.75
     kasarigan
    0.75
    Activations Density 0.092%

    No Known Activations