© 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. 1-CLT-HP
    7. 12293
    Prev
    Next
    INDEX
    Explanations

    researcher

    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
     المعيارى
    -0.69
     wireType
    -0.68
    SharedDtor
    -0.66
     Wicidata
    -0.65
     ويكيپيديا
    -0.63
    RTEE
    -0.63
     Normdatei
    -0.62
     castes
    -0.61
    رشف
    -0.61
     houſe
    -0.61
    POSITIVE LOGITS
     at
    0.51
    Ann
    0.49
     are
    0.49
    ುತ್ತ
    0.48
    ท้าย
    0.46
     said
    0.45
    شة
    0.44
    racuse
    0.43
    beleid
    0.43
     Ann
    0.43
    Activations Density 0.017%

    No Known Activations