© 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. 5-CLT-HP
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    after

    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
    AddTagHelper
    -0.60
     gratuites
    -0.52
    ProgressHUD
    -0.51
    ThroughAttribute
    -0.50
    nages
    -0.50
    KommentareTeilen
    -0.47
    AutoresizingMask
    -0.47
     aspet
    -0.47
     REPLY
    -0.47
    <bos>
    -0.46
    POSITIVE LOGITS
     randomization
    0.58
    Архівовано
    0.57
    herty
    0.53
    もしろ
    0.53
    Geplaatst
    0.53
    ᅠ
    0.52
    operatively
    0.52
    ಂದು
    0.50
    Chham
    0.50
     عز
    0.49
    Activations Density 0.015%

    No Known Activations