© 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. 997
    Prev
    Next
    INDEX
    Explanations

    "little" in different contexts

    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
    AndEndTag
    -0.52
    To
    -0.52
    échange
    -0.51
     to
    -0.50
    grund
    -0.49
     têtes
    -0.48
     circonstances
    -0.48
     verrez
    -0.48
     modalités
    -0.47
     To
    -0.47
    POSITIVE LOGITS
    WriteBarrier
    0.61
     INVENTION
    0.59
    tagHelperRunner
    0.56
    InSection
    0.55
    NUMX
    0.55
    SharedCtor
    0.54
    ChildScrollView
    0.53
     deleg
    0.51
     rehearsals
    0.51
     Nga
    0.50
    Activations Density 0.001%

    No Known Activations