© 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. 92079
    Prev
    Next
    INDEX
    Explanations

    baugh

    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
    mming
    -0.75
    ming
    -0.74
    pland
    -0.71
    rines
    -0.70
    nings
    -0.69
    nable
    -0.65
    MING
    -0.63
     margin
    -0.59
    uing
    -0.59
    necedor
    -0.57
    POSITIVE LOGITS
    UnusedPrivate
    0.80
    LookAnd
    0.62
     Majefty
    0.62
     Ammon
    0.59
     Exactos
    0.59
    Schedulers
    0.59
    Composable
    0.55
     awakeFromNib
    0.54
     الرياضيه
    0.51
     concert
    0.51
    Activations Density 0.035%

    No Known Activations