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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1207
    Prev
    Next
    INDEX
    Explanations

    of

    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
    __(/*!
    -0.65
     bakgrund
    -0.54
     entière
    -0.52
    #+#
    -0.52
    АК
    -0.50
     himo
    -0.48
     verksamhet
    -0.48
    dasarkan
    -0.47
     joaat
    -0.47
    ########.
    -0.46
    POSITIVE LOGITS
     createSlice
    0.73
    LookAnd
    0.63
    tagHelper
    0.63
    StoryboardSegue
    0.58
    fastjson
    0.58
    </tfoot>
    0.56
     living
    0.56
    CppMethod
    0.56
     nakalista
    0.54
    UnusedPrivate
    0.54
    Activations Density 0.001%

    No Known Activations