© 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. 20-CLT-HP
    7. 77356
    Prev
    Next
    INDEX
    Explanations

    technical/unusual words

    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
    complexType
    -0.53
    alek
    -0.52
    alo
    -0.51
    esca
    -0.48
    ured
    -0.46
    nac
    -0.46
     CanadaChoose
    -0.46
    uses
    -0.46
    ée
    -0.45
    nals
    -0.43
    POSITIVE LOGITS
    yntaxException
    0.64
     تانيه
    0.62
     estekak
    0.60
    IVEREF
    0.59
     himo
    0.58
    phi
    0.58
    NewUrlParser
    0.55
    piram
    0.54
    AutoScaleMode
    0.52
    ContentLoaded
    0.52
    Activations Density 0.001%

    No Known Activations