© 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. 4-CLT-HP
    7. 4896
    Prev
    Next
    INDEX
    Explanations

    newly

    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
     armb
    -0.46
     Eſ
    -0.44
     plans
    -0.43
     collars
    -0.42
     judgements
    -0.41
    columbia
    -0.40
     ſeveral
    -0.39
     theſe
    -0.39
     DCM
    -0.39
    orologio
    -0.38
    POSITIVE LOGITS
     defaultstate
    0.90
    Personensuche
    0.85
    UnusedPrivate
    0.75
    Personendaten
    0.73
     formed
    0.72
    CodeAttribute
    0.70
    Portale
    0.69
    complexType
    0.68
     minted
    0.67
     christ
    0.67
    Activations Density 0.003%

    No Known Activations