© 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. 4-CLT-HP
    7. 436
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     betweenstory
    -0.78
    EClass
    -0.77
    TypedDataSet
    -0.73
     calendriers
    -0.72
    gabung
    -0.71
    MLLoader
    -0.70
     IBOutlet
    -0.70
    SharedDtor
    -0.67
    EDEFAULT
    -0.65
     '\\;'
    -0.65
    POSITIVE LOGITS
     The
    0.47
    gpl
    0.40
     voisins
    0.39
     relevant
    0.39
     Auswahl
    0.37
     eccl
    0.36
     Leurs
    0.36
     للمعارف
    0.35
    cinogenicity
    0.35
     selection
    0.35
    Activations Density 0.025%

    No Known Activations