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. 0-CLT-HP
    4. 39174
    Prev
    Next
    INDEX
    Explanations

    names, references, undefined variables

    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
    lic
    -0.75
    empty
    -0.55
     with
    -0.49
    p
    -0.47
     of
    -0.47
     resourceCulture
    -0.47
    au
    -0.46
    k
    -0.46
    aux
    -0.45
    a
    -0.45
    POSITIVE LOGITS
    ſelf
    0.75
     ſtate
    0.68
    MemoryWarning
    0.63
     fubject
    0.63
    horabuena
    0.63
     purpoſe
    0.63
    erapeutics
    0.62
    CPtr
    0.62
     reaſon
    0.61
    idth
    0.61
    Activations Density 0.302%

    No Known Activations