© 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. 5-CLT-HP
    7. 93102
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    RectangleBorder
    -0.85
    SharedDtor
    -0.81
     $_"
    -0.77
    msgTypes
    -0.74
    audiovisuel
    -0.72
     povezave
    -0.72
    InputBorder
    -0.71
    onAttach
    -0.70
     חיצוניים
    -0.69
    vician
    -0.69
    POSITIVE LOGITS
     him
    0.72
     themselves
    0.48
    him
    0.45
     he
    0.45
    der
    0.43
     herself
    0.43
     He
    0.42
    hima
    0.42
     she
    0.41
     himself
    0.40
    Activations Density 0.002%

    No Known Activations