© 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. 5-CLT-HP
    7. 3458
    Prev
    Next
    INDEX
    Explanations

    product information

    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
    Cyfeiriadau
    -0.53
    .
    -0.44
    lagt
    -0.38
     ska
    -0.38
     handelt
    -0.37
     stumped
    -0.35
     ascend
    -0.35
    utte
    -0.34
    رم
    -0.34
    脚注の使い方
    -0.33
    POSITIVE LOGITS
     pleaſure
    0.88
     ſeveral
    0.88
    ChildScrollView
    0.86
     purpoſe
    0.86
     myſelf
    0.84
     reaſon
    0.84
     Monfieur
    0.82
     Offisielt
    0.80
     ſmall
    0.75
     Jefus
    0.75
    Activations Density 0.075%

    No Known Activations