© 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. 91644
    Prev
    Next
    INDEX
    Explanations

    poor

    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
     Dostupné
    -0.67
    SequentialGroup
    -0.48
     محفوظة
    -0.47
    AccessException
    -0.47
    žnost
    -0.45
    SBATCH
    -0.45
     salão
    -0.44
     entendido
    -0.43
    protoimpl
    -0.43
    setTimeout
    -0.42
    POSITIVE LOGITS
     food
    0.79
     foods
    0.76
     foodstuffs
    0.70
     delicacies
    0.69
     fare
    0.68
     snacks
    0.63
     meals
    0.61
    food
    0.61
     materials
    0.60
    Билгалдахарш
    0.60
    Activations Density 0.000%

    No Known Activations