© 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. 76441
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical texts

    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
    WebElementEntity
    -0.85
    addCriterion
    -0.84
    +#+#
    -0.81
    CPtr
    -0.71
    quelize
    -0.69
    DataAnnotations
    -0.69
    matchCondition
    -0.69
     esternos
    -0.67
    NameInMap
    -0.66
    MemoryWarning
    -0.64
    POSITIVE LOGITS
    very
    0.46
     concorso
    0.43
    anovich
    0.42
    OPER
    0.41
     place
    0.41
    place
    0.40
     supportive
    0.40
     very
    0.40
    Всего
    0.39
    away
    0.39
    Activations Density 0.007%

    No Known Activations