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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 612
    Prev
    Next
    INDEX
    Explanations

    Dragging and electrodes

    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
     electrode
    -0.69
     electrodes
    -0.59
     saites
    -0.53
    canActivate
    -0.53
    electrode
    -0.51
     Electrode
    -0.51
     onOptions
    -0.51
     drag
    -0.50
     fritas
    -0.48
    FormBorderStyle
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.63
    Напомним
    0.61
    IVEREF
    0.58
     utafitiHapana
    0.57
    GEBURTS
    0.56
    GOTREF
    0.55
    avir
    0.54
    ########.
    0.54
    /=
    0.53
     summer
    0.52
    Activations Density 0.009%

    No Known Activations