© 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. 92159
    Prev
    Next
    INDEX
    Explanations

    Lengths and ranges

    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
     to
    -0.79
    <bos>
    -0.65
    brainly
    -0.56
    FormTagHelper
    -0.53
    irected
    -0.50
     sepenuhnya
    -0.49
     for
    -0.47
    ****************
    -0.46
    tifully
    -0.45
    ány
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.75
     ligiloj
    0.71
     pinulongan
    0.61
    matchCondition
    0.60
    antası
    0.59
    깐
    0.59
     صوتيه
    0.58
     calendriers
    0.57
    GHIJKLM
    0.55
    StructEnd
    0.54
    Activations Density 0.133%

    No Known Activations