© 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. 1-CLT-HP
    7. 10128
    Prev
    Next
    INDEX
    Explanations

    support

    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
    riwal
    -0.88
    Datuak
    -0.66
    =$?
    -0.65
    __":
    -0.64
     мәкал
    -0.63
    pædia
    -0.63
     صوتيه
    -0.59
    modelBuilder
    -0.59
     Chats
    -0.58
     numberOfRows
    -0.57
    POSITIVE LOGITS
     points
    0.61
     point
    0.60
    point
    0.51
     of
    0.50
     devices
    0.48
     rings
    0.46
     pending
    0.45
     chiffre
    0.45
     followed
    0.44
     Point
    0.44
    Activations Density 0.027%

    No Known Activations