© 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. 91153
    Prev
    Next
    INDEX
    Explanations

    Keys

    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
    keys
    -1.31
     keys
    -1.30
    Keys
    -1.23
     Keys
    -1.16
     KEYS
    -0.92
    KEYS
    -0.88
     enzymes
    -0.74
    ges
    -0.73
    key
    -0.72
    KEY
    -0.63
    POSITIVE LOGITS
    imageshack
    0.56
    ParallelGroup
    0.52
    glEnable
    0.52
    zzleHttp
    0.52
    AllAfrica
    0.51
    hirts
    0.51
     <=",
    0.51
    readObject
    0.50
     >=",
    0.50
    odiment
    0.50
    Activations Density 0.302%

    No Known Activations