© 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. 2129
    Prev
    Next
    INDEX
    Explanations

    *

    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
    "):
    -0.56
     may
    -0.49
     doesn
    -0.49
     مواليد
    -0.48
    "):
    -0.47
     refuses
    -0.47
    Certainly
    -0.46
    ">:
    -0.46
     needs
    -0.46
     certainly
    -0.45
    POSITIVE LOGITS
    FS
    0.59
    AU
    0.58
     OMITBAD
    0.58
     étoient
    0.56
     AUR
    0.56
    W
    0.54
    WAS
    0.54
     avoient
    0.54
    AR
    0.53
     käns
    0.52
    Activations Density 0.000%

    No Known Activations