© 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. 1-CLT-HP
    7. 15302
    Prev
    Next
    INDEX
    Explanations

    derived

    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
     Derived
    -0.88
    Derived
    -0.82
     derived
    -0.73
    /**
    -0.68
    FTFY
    -0.68
    ricians
    -0.68
    anteen
    -0.66
     ftate
    -0.65
     Theſe
    -0.64
     traseiro
    -0.62
    POSITIVE LOGITS
     مشين
    0.53
     lenker
    0.48
    ,
    0.46
    principalColumn
    0.43
    ModelAttribute
    0.43
    SharedCtor
    0.41
    Meme
    0.41
    FormBuilder
    0.41
     timmar
    0.40
    зербай
    0.39
    Activations Density 0.013%

    No Known Activations