© 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. 1-CLT-HP
    7. 9016
    Prev
    Next
    INDEX
    Explanations

    concrete

    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
    fromnode
    -0.64
    IsContent
    -0.58
     concrete
    -0.57
    >{@
    -0.54
    AndEndTag
    -0.50
    ACEAE
    -0.50
    concrete
    -0.49
     Exploit
    -0.49
    ochet
    -0.49
    TagMode
    -0.49
    POSITIVE LOGITS
    BeginContext
    0.63
    ViewImports
    0.61
    glDelete
    0.50
    неопр
    0.50
    DeleteMapping
    0.49
    errHandler
    0.48
     estekak
    0.47
    glTranslatef
    0.44
    Портал
    0.44
     getItemCount
    0.44
    Activations Density 0.221%

    No Known Activations