© 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. 9611
    Prev
    Next
    INDEX
    Explanations

    Locations and objects

    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
    bys
    -0.47
     BoxDecoration
    -0.46
    pads
    -0.42
     transfer
    -0.42
    oxin
    -0.42
    ైన
    -0.42
    arau
    -0.41
    mallow
    -0.41
    roaches
    -0.41
    agog
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.71
     Colonies
    0.68
    OGND
    0.67
     myſelf
    0.64
     صوتيه
    0.64
     تضيفلها
    0.63
     Monfieur
    0.62
     Majefty
    0.61
    ErrUnexpectedEOF
    0.60
     Houſe
    0.60
    Activations Density 0.035%

    No Known Activations