© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73712
    Prev
    Next
    INDEX
    Explanations

    Programming/technical code

    np_max-act-logits · 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
    ̍
    -0.51
     للمعارف
    -0.50
     scolaire
    -0.46
     fermés
    -0.43
    udnio
    -0.43
     bune
    -0.42
     betreft
    -0.40
     religieuse
    -0.40
     مرئيه
    -0.40
    photobucket
    -0.40
    POSITIVE LOGITS
    }))
    0.85
     XCTest
    0.71
    "])
    0.67
    MigrationBuilder
    0.65
    ])).
    0.64
     intptr
    0.64
    ])))
    0.63
    InjectAttribute
    0.63
    tagHelperRunner
    0.62
    SOUNDBITE
    0.62
    Activations Density 0.005%

    No Known Activations