© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92626
    Prev
    Next
    INDEX
    Explanations

    health

    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
    tagHelperRunner
    -1.11
    RectangleBorder
    -0.91
     ویکی‌پدیا
    -0.90
    providedIn
    -0.88
    extAlignment
    -0.88
    /*
    -0.86
    +#+#
    -0.86
    InstanceState
    -0.84
     MainAxisSize
    -0.84
    DebuggerNonUser
    -0.82
    POSITIVE LOGITS
    PY
    0.45
     met
    0.44
     accepted
    0.42
    ポ
    0.41
     vo
    0.40
    PG
    0.40
     pag
    0.40
     пу
    0.40
     of
    0.39
     Púb
    0.38
    Activations Density 0.120%

    No Known Activations