© 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. 0-CLT-HP
    7. 42240
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
     يتيمه
    -0.73
     protoimpl
    -0.72
    AccessorTable
    -0.69
    EDEFAULT
    -0.68
    WebVitals
    -0.66
    StringProperty
    -0.65
     ddelweddau
    -0.65
    期刊论文
    -0.64
    PYX
    -0.63
    IndentedString
    -0.63
    POSITIVE LOGITS
     the
    1.21
     this
    0.83
     it
    0.78
     a
    0.77
     that
    0.72
     is
    0.69
     its
    0.66
     what
    0.66
     their
    0.58
     these
    0.56
    Activations Density 0.168%

    No Known Activations