© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91866
    Prev
    Next
    INDEX
    Explanations

    list

    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
     للاسماء
    -0.67
    featureID
    -0.64
    IVEREF
    -0.63
     الاطلاع
    -0.63
    出版年
    -0.62
    oa̍t
    -0.60
    balleur
    -0.59
    دانشنامهٔ
    -0.58
    انيف
    -0.57
    rungsseite
    -0.57
    POSITIVE LOGITS
    SizeMode
    0.46
     on
    0.46
     of
    0.46
     Zustand
    0.46
    fillna
    0.45
    vivencia
    0.44
    :
    0.44
    åg
    0.44
     Mata
    0.43
    onoma
    0.43
    Activations Density 0.036%

    No Known Activations