© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    proper nouns/names

    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
    StoryboardSegue
    -0.66
     riuscito
    -0.59
    AndEndTag
    -0.52
    Clik
    -0.51
    MockMvc
    -0.49
    ########.
    -0.49
    enumi
    -0.48
    UrlResolution
    -0.48
    featureID
    -0.47
    /******/
    -0.46
    POSITIVE LOGITS
     book
    0.57
     ApiException
    0.54
     map
    0.54
     aceptas
    0.54
     variable
    0.54
     signature
    0.54
     dossier
    0.53
    älä
    0.53
     AUSSI
    0.53
    руппа
    0.52
    Activations Density 0.014%

    No Known Activations