© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    fix

    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
     Bioaccumulative
    -0.53
    Morfologia
    -0.49
    gebnis
    -0.49
    <bos>
    -0.45
     autorità
    -0.44
    eney
    -0.44
    蜒
    -0.44
     voulons
    -0.42
    いたり
    -0.41
    colade
    -0.41
    POSITIVE LOGITS
    webElementXpaths
    0.66
    UnsafeEnabled
    0.60
    Jereo
    0.60
    )++;
    0.59
    tanleria
    0.58
    ousands
    0.57
    RegistryLite
    0.56
    ThemeOverlay
    0.56
    CodedInputStream
    0.56
     ErrIntOverflow
    0.56
    Activations Density 0.001%

    No Known Activations