© 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. 5-CLT-HP
    7. 98209
    Prev
    Next
    INDEX
    Explanations

    Named entities

    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
    <bos>
    -1.39
    Geplaatst
    -0.85
    Portale
    -0.79
     kasarigan
    -0.77
    BeginContext
    -0.76
    WriteBarrier
    -0.75
    enumii
    -0.68
    Rè
    -0.67
    )».
    -0.63
    AndEndTag
    -0.63
    POSITIVE LOGITS
    енча
    0.56
     franca
    0.48
     ddelweddau
    0.47
     Regard
    0.46
     yürü
    0.45
    almaz
    0.44
     differently
    0.43
    밌
    0.41
    ærk
    0.40
    ēju
    0.40
    Activations Density 0.050%

    No Known Activations