© 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. 42496
    Prev
    Next
    INDEX
    Explanations

    Aid

    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
    Aid
    -0.65
     Aid
    -0.60
    ing
    -0.59
    ING
    -0.51
    
    -0.51
    Difficulty
    -0.47
    TabIndex
    -0.46
    wigs
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    jkl
    -0.44
    POSITIVE LOGITS
    WithMany
    0.77
    __':
    0.70
    onAttach
    0.68
    uktur
    0.62
    رشف
    0.60
     EClass
    0.60
     Monfieur
    0.60
    ChildScrollView
    0.59
     vectorielle
    0.58
    moiselle
    0.57
    Activations Density 0.073%

    No Known Activations