© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    like as

    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
    cythe
    -0.45
    cel
    -0.42
    wpdb
    -0.40
    bau
    -0.38
     purposes
    -0.38
    uch
    -0.36
    ituri
    -0.35
     front
    -0.35
    ytu
    -0.35
    balanceOf
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.84
     发表于
    0.78
     '{@
    0.72
    userdetails
    0.72
     propOrder
    0.71
    ConstraintMaker
    0.70
     contextLoads
    0.69
    CppMethod
    0.67
     дописавши
    0.65
     piattaforma
    0.64
    Activations Density 0.002%

    No Known Activations