© 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. 94674
    Prev
    Next
    INDEX
    Explanations

    assistance

    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
     marks
    -0.55
    RenderAtEndOf
    -0.52
    anj
    -0.47
     dit
    -0.46
    ManagedBean
    -0.45
     réception
    -0.45
    ברה
    -0.44
    setFirstName
    -0.44
     dormitórios
    -0.44
    alnız
    -0.44
    POSITIVE LOGITS
    +:+
    0.71
     '{@
    0.64
    تقاوى
    0.57
    <()>
    0.56
    amoan
    0.56
    +#+#
    0.56
     informée
    0.54
    estries
    0.54
    seteq
    0.54
    Rptr
    0.54
    Activations Density 0.178%

    No Known Activations