© 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. 4-CLT-HP
    7. 178
    Prev
    Next
    INDEX
    Explanations

    mic

    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
    __(/*!
    -0.53
     Ngb
    -0.52
    mags
    -0.50
    (@"%@",
    -0.49
    modb
    -0.49
    LS
    -0.48
    astéroïdes
    -0.48
     rospy
    -0.48
     gyhoeddwyd
    -0.47
    tagext
    -0.46
    POSITIVE LOGITS
     Year
    0.59
    +#+#
    0.58
    Year
    0.56
     Years
    0.51
    Years
    0.49
     YEAR
    0.47
    Бахар
    0.47
    icioso
    0.47
    Override
    0.44
    olak
    0.44
    Activations Density 0.008%

    No Known Activations