Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73796
    Prev
    Next
    INDEX
    Explanations

    number

    np_max-act-logits · 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
    antd
    -0.51
     condado
    -0.46
    WriteLiteral
    -0.43
    odly
    -0.41
    UL
    -0.40
    žin
    -0.40
    EndInit
    -0.40
    semb
    -0.40
    Po
    -0.40
    poy
    -0.39
    POSITIVE LOGITS
    DockStyle
    0.68
    ropoda
    0.65
     cdti
    0.64
    âme
    0.61
    ➟
    0.61
     crdi
    0.59
     dafs
    0.59
    μως
    0.58
     frie
    0.57
     ARXIV
    0.56
    Activations Density 0.000%

    No Known Activations