Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74245
    Prev
    Next
    INDEX
    Explanations

    Citations and references

    np_max-act-logits · 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
     myſelf
    -0.61
    contentLoaded
    -0.54
    ſelf
    -0.52
     poffible
    -0.51
    ौर
    -0.51
     purpoſe
    -0.50
     themſelves
    -0.50
    labelledby
    -0.49
     poffe
    -0.49
     tins
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.77
    esModule
    0.53
    GEBURTS
    0.50
    Referensi
    0.48
    ⎩
    0.47
    alamu
    0.46
    #+#
    0.46
    didSet
    0.45
     BrowserModule
    0.45
    তথ্যসূত্র
    0.44
    Activations Density 0.106%

    No Known Activations