© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5582
    Prev
    Next
    INDEX
    Explanations

    direction and movement

    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
    -0.63
     of
    -0.62
    发表于
    -0.56
     ModelExpression
    -0.55
    BagConstraints
    -0.54
     BoxDecoration
    -0.53
    antaranya
    -0.52
     rueda
    -0.52
    of
    -0.51
    ">—
    -0.51
    POSITIVE LOGITS
     between
    0.70
     the
    0.68
     @"/
    0.59
     carrying
    0.59
    Distribuzione
    0.53
     studying
    0.52
    AddTagHelper
    0.52
    rabi
    0.50
     Carrying
    0.50
    ittin
    0.49
    Activations Density 0.001%

    No Known Activations