© 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. 93729
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    leton
    -0.62
    ori
    -0.57
    oria
    -0.56
     on
    -0.53
    ORIA
    -0.53
    umann
    -0.53
    ところです
    -0.52
     it
    -0.52
    rim
    -0.50
    uner
    -0.50
    POSITIVE LOGITS
    ized
    1.08
    Personendaten
    0.84
    ization
    0.83
    izing
    0.77
    adays
    0.76
    ed
    0.75
    theless
    0.75
     tartalomajánló
    0.74
    AndEndTag
    0.73
     فريبيس
    0.72
    Activations Density 0.172%

    No Known Activations