© 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. 40030
    Prev
    Next
    INDEX
    Explanations

    olds

    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
    AndEndTag
    -1.16
     étoient
    -1.00
     Efq
    -1.00
     feroit
    -0.99
    makeConstraints
    -0.98
     ainfi
    -0.95
     stone
    -0.94
     raiſ
    -0.94
     quæ
    -0.93
    ſelf
    -0.93
    POSITIVE LOGITS
     I
    0.82
     l
    0.69
     
    0.66
    '
    0.65
     De
    0.62
     of
    0.62
     O
    0.62
     i
    0.60
     de
    0.59
     E
    0.58
    Activations Density 0.297%

    No Known Activations