© 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. 5-CLT-HP
    7. 91616
    Prev
    Next
    INDEX
    Explanations

    Politics, news, reports

    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
    IUrlHelper
    -0.71
    NUMX
    -0.65
    Portály
    -0.65
    angsaan
    -0.59
    ulipas
    -0.58
    kaido
    -0.58
    endphp
    -0.57
    adaptiveStyles
    -0.57
    dafx
    -0.57
     miljoner
    -0.56
    POSITIVE LOGITS
     behind
    0.71
     Behind
    0.58
    behind
    0.56
     BEHIND
    0.55
    XtraReports
    0.52
    Behind
    0.48
     derrière
    0.47
    ’
    0.47
    yethyl
    0.46
     amongst
    0.46
    Activations Density 0.001%

    No Known Activations