© 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. 0-CLT-HP
    7. 94490
    Prev
    Next
    INDEX
    Explanations

    presence

    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
     presence
    -2.66
    presence
    -2.20
     Presence
    -2.09
    Presence
    -1.87
     présence
    -1.73
     presencia
    -1.52
     aanwezig
    -1.32
     presença
    -1.30
     presenza
    -1.22
     kehadiran
    -1.13
    POSITIVE LOGITS
     of
    0.96
     của
    0.51
    tagHelperRunner
    0.49
     narkoba
    0.49
     razón
    0.46
     allá
    0.46
     accidente
    0.45
     rêves
    0.45
     célèbres
    0.45
     infección
    0.45
    Activations Density 1.510%

    No Known Activations