© 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. 4-CLT-HP
    7. 4345
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    gonic
    -0.62
    نگار
    -0.52
    fastjson
    -0.50
    ärin
    -0.49
    kosh
    -0.49
    iose
    -0.48
    roaches
    -0.47
     viewDidLoad
    -0.47
    AnimationsModule
    -0.46
    vartis
    -0.46
    POSITIVE LOGITS
     beginnetje
    0.66
    NameInMap
    0.60
     transfieras
    0.59
    Tikang
    0.58
    nalités
    0.57
     passes
    0.56
     PyTuple
    0.55
     ElementRef
    0.55
     HFILL
    0.55
    <bos>
    0.54
    Activations Density 0.015%

    No Known Activations