© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97925
    Prev
    Next
    INDEX
    Explanations

    tic

    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
    }))
    -0.59
    //
    -0.53
    ContextHolder
    -0.50
     eccl
    -0.48
     handleChange
    -0.47
    "/>
    -0.47
    Slf
    -0.47
    ?></
    -0.46
     ?></
    -0.44
    éu
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.89
    GEBURTSDATUM
    0.77
    LookAnd
    0.77
    хьтан
    0.75
     autorytatywna
    0.74
    Datuak
    0.72
     ddelweddau
    0.71
    GTCX
    0.70
    posedge
    0.70
     utafitiHapana
    0.69
    Activations Density 0.001%

    No Known Activations