© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    Park or park

    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
    الحياه
    -0.57
    dfrac
    -0.53
    HasMaxLength
    -0.50
    NegativeButton
    -0.50
    ovács
    -0.50
    dorfer
    -0.49
    $_['
    -0.48
     Devices
    -0.48
     AssemblyVersion
    -0.47
     ويكيپيديا
    -0.47
    POSITIVE LOGITS
    rrggbb
    0.72
     MainAxisSize
    0.61
    AndEndTag
    0.56
     Tapia
    0.56
     BoxFit
    0.54
    Tikang
    0.54
    hyrchwyd
    0.54
    IContainer
    0.54
    bunda
    0.54
    Autoritní
    0.52
    Activations Density 0.155%

    No Known Activations