© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    photons and jazz

    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
    OGND
    -0.98
     CreateTagHelper
    -0.90
     ujednoznacz
    -0.82
     defaultstate
    -0.81
     <>",
    -0.79
    Personendaten
    -0.77
     ويكيميديا
    -0.75
     democrática
    -0.71
    SourceChecksum
    -0.68
    IUrlHelper
    -0.68
    POSITIVE LOGITS
    ically
    0.76
    ism
    0.63
    ized
    0.62
    ess
    0.59
    istic
    0.59
    ally
    0.58
     in
    0.56
    iness
    0.56
    istically
    0.56
    '
    0.55
    Activations Density 0.173%

    No Known Activations