© 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. 0-CLT-HP
    7. 92168
    Prev
    Next
    INDEX
    Explanations

    Nuclear

    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
    <bos>
    -0.50
     Superhosts
    -0.45
     Leopoldo
    -0.45
     RIGHTS
    -0.45
    +:+
    -0.43
    featureID
    -0.42
    cdef
    -0.41
    richTextPanel
    -0.41
     lobo
    -0.41
     Álvaro
    -0.40
    POSITIVE LOGITS
     Weapons
    0.68
     Builds
    0.66
    ValueStyle
    0.65
     Treats
    0.65
     Players
    0.64
    ResponseWriter
    0.64
     Winaray
    0.64
     Experiences
    0.63
     Suffer
    0.63
     Walkover
    0.63
    Activations Density 0.058%

    No Known Activations