© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1936
    Prev
    Next
    INDEX
    Explanations

    tab

    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
    IBOutlet
    -0.50
     صوتيه
    -0.48
    SerializedSize
    -0.45
     auras
    -0.45
    {~
    -0.45
     gauze
    -0.42
     grains
    -0.42
    Normdaten
    -0.42
    AccessorTable
    -0.41
     thermos
    -0.41
    POSITIVE LOGITS
    featureID
    0.66
    Datuak
    0.65
     colorés
    0.62
     originaux
    0.61
    beled
    0.60
    bed
    0.59
    balleur
    0.57
     StringTokenizer
    0.57
     genoux
    0.56
     lettre
    0.55
    Activations Density 0.001%

    No Known Activations