© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44230
    Prev
    Next
    INDEX
    Explanations

    Transistors/electronics

    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
    i
    -0.83
    ed
    -0.81
    thâu
    -0.77
     itſelf
    -0.75
    e
    -0.75
     betweenstory
    -0.74
     raiſ
    -0.71
    adecimal
    -0.69
    toes
    -0.68
    eer
    -0.68
    POSITIVE LOGITS
    dorfer
    0.56
     of
    0.56
    matchCondition
    0.56
    ness
    0.52
    HasForeignKey
    0.51
    rospy
    0.51
    '
    0.49
    preuve
    0.47
     and
    0.47
     in
    0.47
    Activations Density 0.046%

    No Known Activations