© 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. 92925
    Prev
    Next
    INDEX
    Explanations

    strength

    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
     strength
    -1.87
    strength
    -1.82
     Strength
    -1.73
    Strength
    -1.70
     STRENGTH
    -1.48
     strengths
    -1.47
     Strengths
    -1.33
    STRENGTH
    -1.30
     Stärke
    -1.22
    Strengths
    -1.20
    POSITIVE LOGITS
    ,
    0.95
    <eos>
    0.66
    .
    0.64
     (
    0.62
     for
    0.62
     La
    0.60
     
    0.59
     Le
    0.59
     "
    0.58
     |
    0.57
    Activations Density 1.402%

    No Known Activations