© 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. 5-CLT-HP
    7. 2876
    Prev
    Next
    INDEX
    Explanations

    identifiers

    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
    SharedCtor
    -0.61
    setVerticalGroup
    -0.60
     Italijani
    -0.59
     referenties
    -0.57
     esternos
    -0.55
     gynhyrchwyd
    -0.54
    évaluateur
    -0.52
    postsleuth
    -0.50
     ostavi
    -0.50
    jzen
    -0.48
    POSITIVE LOGITS
    routeProvider
    0.72
    stateProvider
    0.56
    Traceback
    0.51
     Bounty
    0.50
     Roskov
    0.48
     QName
    0.48
    abstractmethod
    0.47
     Norman
    0.47
     Nana
    0.46
    ngOnInit
    0.46
    Activations Density 0.004%

    No Known Activations