© 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. 90638
    Prev
    Next
    INDEX
    Explanations

    form

    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
     form
    -0.43
     for
    -0.36
     untuk
    -0.35
     async
    -0.35
    のご
    -0.35
    前で
    -0.34
     поводу
    -0.34
     forma
    -0.34
     gu
    -0.33
     PRIOR
    -0.33
    POSITIVE LOGITS
    MigrationBuilder
    0.94
    AndEndTag
    0.93
     tartalomajánló
    0.93
     purpoſe
    0.93
    principalTable
    0.89
     '\\;'
    0.89
     autorytatywna
    0.89
     Theſe
    0.87
    OGND
    0.87
     estekak
    0.86
    Activations Density 0.032%

    No Known Activations