© 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. 43193
    Prev
    Next
    INDEX
    Explanations

    Action 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
    They
    -0.64
    they
    -0.54
     kanilang
    -0.52
    <bos>
    -0.50
     Они
    -0.49
     они
    -0.46
     Ellos
    -0.46
    I
    -0.43
     вони
    -0.42
    “
    -0.42
    POSITIVE LOGITS
     us
    0.93
     me
    0.87
     Picchu
    0.70
    peño
    0.69
     useRouter
    0.69
    ffindor
    0.68
    примеча
    0.67
    CompleteListener
    0.65
    brities
    0.65
    gants
    0.64
    Activations Density 0.029%

    No Known Activations