© 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. 0-CLT-HP
    7. 43049
    Prev
    Next
    INDEX
    Explanations

    fetching, handler

    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
     consultato
    -0.73
     fetching
    -0.73
    ValueStyle
    -0.66
    SequentialGroup
    -0.65
    الحياه
    -0.65
     Paulina
    -0.65
     XNUMX
    -0.64
    genuine
    -0.64
     Anam
    -0.64
    enumii
    -0.63
    POSITIVE LOGITS
    CPtr
    0.53
     دیکھیے
    0.50
     ilg
    0.45
     Har
    0.45
    SuppressMessage
    0.43
    ніципалі
    0.43
     kaarangay
    0.43
    CopyWith
    0.42
    profen
    0.41
    <0xEF>
    0.40
    Activations Density 0.066%

    No Known Activations