© 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. 91232
    Prev
    Next
    INDEX
    Explanations

    to

    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
    AccessorTable
    -0.84
     <=",
    -0.77
    #+#
    -0.73
    ⓧ
    -0.73
    AutoField
    -0.68
    Diweddarwch
    -0.66
    PyExc
    -0.65
    XmlAccessorType
    -0.65
    addCriterion
    -0.65
     <>",
    -0.65
    POSITIVE LOGITS
     pertenece
    0.51
     חיצוניים
    0.43
     commercio
    0.43
     finnes
    0.41
    Internal
    0.40
     tæ
    0.40
     احتم
    0.40
    Externe
    0.40
     bäst
    0.40
    acité
    0.39
    Activations Density 0.003%

    No Known Activations